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

    Neuronpedia

    INDEX
    Explanations

    negative forms of contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     selected
    -0.56
    aya
    -0.55
     do
    -0.54
     DO
    -0.54
    O
    -0.54
     K
    -0.53
    EntryPoint
    -0.52
     group
    -0.51
     type
    -0.50
    DO
    -0.50
    POSITIVE LOGITS
     wasnt
    0.97
    twas
    0.89
    '],
    0.82
     useAppContext
    0.81
     isnt
    0.80
    t
    0.80
    Зноскі
    0.79
    theless
    0.78
     Мексичка
    0.77
    `,
    0.77
    Act Density 0.080%

    No Known Activations