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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "is" and various punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.06
    2:0.04
    3:0.07
    4:0.28
    5:0.07
    6:0.07
    7:0.08
    8:0.04
    9:0.05
    10:0.06
    11:0.07
    Negative Logits
     Quote
    -3.15
     Here
    -2.99
     Beet
    -2.96
     Judging
    -2.83
     Assuming
    -2.77
     Suppose
    -2.69
     Enter
    -2.63
     Helpful
    -2.60
     Click
    -2.59
     Reading
    -2.58
    POSITIVE LOGITS
     OPS
    3.40
    INTER
    3.04
     FSA
    2.96
     weap
    2.88
     scrim
    2.83
     frail
    2.79
     UNHCR
    2.73
     reluct
    2.67
     SOU
    2.66
     exting
    2.61
    Act Density 0.000%

    No Known Activations