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

    Neuronpedia

    INDEX
    Explanations

    occurrences of parenthesis or opening brackets in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    __':
    -0.60
    __':
    -0.58
    PreferredItem
    -0.54
     Becoming
    -0.53
    principalColumn
    -0.52
     cuer
    -0.51
    closePath
    -0.51
    __":
    -0.50
    styleType
    -0.50
    Sze
    -0.50
    POSITIVE LOGITS
    
    0.73
    athyroid
    0.65
    DataAnnotations
    0.63
     disponibilités
    0.63
     Reverso
    0.62
    estacks
    0.62
    ttino
    0.62
    PDM
    0.59
    évaluateur
    0.59
    '][$
    0.58
    Act Density 0.009%

    No Known Activations