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

    Neuronpedia

    INDEX
    Explanations

    sentences or fragments that imply consequences or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.78
     doInBackground
    -0.77
     Мексичка
    -0.75
    ...]
    -0.74
     estekak
    -0.74
    ...')
    -0.73
    ...</
    -0.73
    MigrationBuilder
    -0.72
    …]
    -0.71
    Portály
    -0.70
    POSITIVE LOGITS
    '
    0.62
    cocho
    0.56
     olmayan
    0.48
    ’
    0.47
     görün
    0.47
    ecuzione
    0.47
     Runde
    0.47
     olmad
    0.47
     kväll
    0.47
     kveld
    0.46
    Act Density 0.220%

    No Known Activations