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

    Neuronpedia

    INDEX
    Explanations

    quotations and dialogue markers in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Мексичка
    -1.33
     autorytatywna
    -1.30
    Portale
    -1.19
     itſelf
    -1.13
    ſelf
    -1.12
    InjectAttribute
    -1.12
     myſelf
    -1.09
     defaultstate
    -1.08
     nahilalakip
    -1.08
    tvguidetime
    -1.06
    POSITIVE LOGITS
    ”
    0.81
     
    0.77
    “
    0.75
     “
    0.69
    ’
    0.69
    "
    0.68
      
    0.68
     K
    0.64
    i
    0.63
     I
    0.62
    Act Density 0.016%

    No Known Activations