© 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. 1768
    Prev
    Next
    INDEX
    Explanations

    references to hiring or employment actions

    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
    ramid
    -0.94
    田
    -0.81
    kind
    -0.80
    URE
    -0.78
    layer
    -0.78
    story
    -0.77
    ガ
    -0.75
    rollment
    -0.71
    opening
    -0.71
    inning
    -0.70
    POSITIVE LOGITS
     Scher
    0.69
     Hust
    0.69
     Aman
    0.68
     Kop
    0.64
     Chap
    0.64
     comedian
    0.63
     recognizable
    0.63
     viz
    0.61
     Yog
    0.61
     Mub
    0.61
    Activations Density 0.087%

    No Known Activations