© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2388
    Prev
    Next
    INDEX
    Explanations

    proper names of actors and directors in film contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    court
    -0.60
     contractor
    -0.58
    eff
    -0.57
     volunteer
    -0.57
    lust
    -0.55
    hetto
    -0.55
     bidder
    -0.54
    selves
    -0.53
    cill
    -0.52
    sole
    -0.52
    POSITIVE LOGITS
    igun
    0.80
    ヘラ
    0.76
    \":
    0.68
    icism
    0.65
    Animation
    0.62
    �
    0.62
    aretz
    0.61
    ification
    0.60
    }:
    0.59
    xit
    0.58
    Activations Density 0.248%

    No Known Activations