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

    Neuronpedia

    INDEX
    Explanations

    legal terms and conditions related to election procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.72
    -
    -0.58
     almost
    -0.58
     lots
    -0.57
    ed
    -0.57
    +
    -0.56
     pretty
    -0.55
     three
    -0.55
    db
    -0.54
     four
    -0.53
    POSITIVE LOGITS
     purpoſe
    1.06
     Majefty
    1.05
     vectorielle
    0.97
     myſelf
    0.95
     '\\;'
    0.93
     pleaſure
    0.92
     Assyrian
    0.91
     cauſe
    0.90
     métallique
    0.89
     Shakspeare
    0.88
    Act Density 0.403%

    No Known Activations