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

    Neuronpedia

    INDEX
    Explanations

    words related to discussions and acknowledgments in research contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    väl
    -0.63
    må
    -0.58
     féminine
    -0.55
     parete
    -0.53
     littéraire
    -0.52
     remarquer
    -0.52
     szép
    -0.52
     creativos
    -0.52
     övers
    -0.52
     digitais
    -0.52
    POSITIVE LOGITS
    matchCondition
    0.63
    CPtr
    0.62
    ագրություններ
    0.62
    曖昧さ回避
    0.61
    ThroughAttribute
    0.60
    UnitTesting
    0.60
    urlpatterns
    0.59
    mybatisplus
    0.59
    허
    0.59
    KommentareTeilen
    0.56
    Act Density 0.008%

    No Known Activations