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

    Neuronpedia

    INDEX
    Explanations

    specific character names and their interactions in a narrative context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Демографія
    -0.98
    ſelves
    -0.96
    ReusableCell
    -0.93
    '},
    -0.90
     myſelf
    -0.88
    ſelf
    -0.86
     $_"
    -0.85
    IsMutable
    -0.85
     Мексичка
    -0.84
    ьаж
    -0.84
    POSITIVE LOGITS
     sitten
    0.53
    又有
    0.52
    ↵↵
    0.48
     goes
    0.48
     Then
    0.47
    ↵
    0.46
    ...
    0.46
    用
    0.46
    又
    0.45
     pod
    0.45
    Act Density 0.250%

    No Known Activations