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

    Neuronpedia

    INDEX
    Explanations

    negative constructions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -0.84
     disambiguazione
    -0.82
    s
    -0.79
    ?>">
    -0.73
    gridy
    -0.71
     isNameExpr
    -0.70
     azzurro
    -0.70
     collègues
    -0.69
     bílá
    -0.67
    schule
    -0.66
    POSITIVE LOGITS
     isn
    0.84
     couldn
    0.81
     aren
    0.78
     shouldn
    0.77
    couldn
    0.76
     wasn
    0.76
     don
    0.75
     won
    0.72
     doesn
    0.71
     didn
    0.70
    Act Density 0.063%

    No Known Activations