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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 862
    Prev
    Next
    INDEX
    Explanations

    the word "which" in various 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
    ingers
    -0.62
    worth
    -0.58
    ascript
    -0.58
    comed
    -0.57
    INST
    -0.57
    ickr
    -0.57
    second
    -0.56
    inn
    -0.56
    icky
    -0.56
    videos
    -0.56
    POSITIVE LOGITS
     differs
    0.80
     includes
    0.79
     entails
    0.78
     corresponds
    0.77
     revolves
    0.76
     relates
    0.73
     involves
    0.73
     consists
    0.72
     contains
    0.72
     follows
    0.71
    Activations Density 0.029%

    No Known Activations