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

    Neuronpedia

    INDEX
    Explanations

    academic phrases indicating research findings or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    timb
    -0.64
     Rost
    -0.64
     disambiguazione
    -0.58
     highlighting
    -0.56
    Fac
    -0.56
     المعيارى
    -0.56
    felt
    -0.53
    chum
    -0.52
     comments
    -0.52
     commentaire
    -0.52
    POSITIVE LOGITS
    enderror
    0.62
     zufolge
    0.60
     BoxFit
    0.59
    ciuto
    0.58
    حياته
    0.56
    ukone
    0.54
     efectivamente
    0.53
    ActionCreators
    0.53
    Produzione
    0.52
    맞
    0.52
    Act Density 0.493%

    No Known Activations