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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the conditions under which compensation or accountability may apply

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↘
    -0.45
    ście
    -0.43
    imana
    -0.42
    Sources
    -0.42
     Lieber
    -0.42
    licite
    -0.41
     loc
    -0.41
    tib
    -0.41
     seria
    -0.40
    ژن
    -0.40
    POSITIVE LOGITS
     Roskov
    0.81
    seamnă
    0.78
     BorderRadius
    0.77
    setVerticalGroup
    0.73
     Reverso
    0.73
     AttributeSet
    0.72
     Wiktionnaire
    0.71
     doesn
    0.68
     kasarigan
    0.67
    未必
    0.65
    Act Density 0.453%

    No Known Activations