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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "All" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.84
    aparte
    -0.78
     Penrose
    -0.75
     murmur
    -0.71
    itename
    -0.70
    Jeografia
    -0.68
    ultuous
    -0.68
    ratulations
    -0.68
    躇
    -0.67
    ilibrium
    -0.67
    POSITIVE LOGITS
     All
    1.57
    All
    1.36
    all
    0.90
     all
    0.85
     ALL
    0.83
    ALL
    0.79
    allo
    0.60
     所有
    0.58
    LastModified
    0.58
    endsection
    0.53
    Act Density 0.040%

    No Known Activations