© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 2588
    Prev
    Next
    INDEX
    Explanations

    the phrase "Eye of Terror" and its variations

    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
    ictional
    -0.84
    amines
    -0.69
    auga
    -0.69
     obsc
    -0.68
     smokes
    -0.63
     strikes
    -0.63
    irit
    -0.62
    ushes
    -0.61
     smells
    -0.60
    ilit
    -0.60
    POSITIVE LOGITS
    ahime
    0.84
     Zed
    0.70
    arna
    0.70
    ivan
    0.68
     Nerd
    0.67
    nai
    0.65
     Remem
    0.65
    nature
    0.64
     NEC
    0.64
    eto
    0.64
    Activations Density 0.073%

    No Known Activations