Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and expressions indicating code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hard
    -0.63
     Nes
    -0.62
     Hard
    -0.55
    ↵↵↵
    -0.54
    Hard
    -0.53
    velt
    -0.53
     stuff
    -0.50
     Tait
    -0.49
     Dol
    -0.49
     enough
    -0.49
    POSITIVE LOGITS
    AddTagHelper
    1.01
    ArgsConstructor
    0.97
    IntoConstraints
    0.93
    enumi
    0.93
    ConstraintMaker
    0.87
    awtextra
    0.85
    帖最后由
    0.84
    GEBURTS
    0.82
     HasFactory
    0.80
    RectangleBorder
    0.78
    Act Density 0.021%

    No Known Activations