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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "call" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chè
    -0.48
     bő
    -0.44
    nage
    -0.44
     detri
    -0.43
    age
    -0.43
    ორ
    -0.42
     /\.
    -0.42
    mtd
    -0.41
     slight
    -0.41
    noh
    -0.41
    POSITIVE LOGITS
     bluff
    0.93
     attention
    0.90
     quits
    0.88
     names
    0.82
     NSCoder
    0.76
     NAMES
    0.76
     foul
    0.72
     spade
    0.71
     Names
    0.71
     into
    0.71
    Act Density 0.074%

    No Known Activations