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

    Neuronpedia

    INDEX
    Explanations

    references to "heavy" and associated terminology with varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.65
    NOPQRST
    -0.63
     مرئيه
    -0.62
    tvguidetime
    -0.60
    cibly
    -0.59
    parsedMessage
    -0.58
    cerely
    -0.58
     createSlice
    -0.57
    تقاوى
    -0.57
     Zähne
    -0.56
    POSITIVE LOGITS
     duty
    1.16
     Duty
    1.02
    duty
    0.99
    Duty
    0.96
     DUTY
    0.93
     hitters
    0.87
    weights
    0.86
    SourceChecksum
    0.79
     hitter
    0.76
    WEIGHT
    0.65
    Act Density 0.206%

    No Known Activations