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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or entities involved in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    numerusform
    -0.64
    etheless
    -0.63
    URDAY
    -0.62
    tioner
    -0.62
     
    -0.62
    ⁣
    -0.61
     ErrIntOverflow
    -0.59
     ‍
    -0.58
    ADVERTISEMENT
    -0.58
    ividual
    -0.57
    POSITIVE LOGITS
    faßt
    0.75
     pesce
    0.59
     giebt
    0.59
    laß
    0.58
     naturali
    0.55
     mußte
    0.55
     ويكيپيديا
    0.54
     normaux
    0.54
     tewas
    0.54
     sottile
    0.54
    Act Density 0.539%

    No Known Activations