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

    Neuronpedia

    INDEX
    Explanations

    terms indicating certainty or clarity about a situation or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVEREF
    -0.70
     Abbé
    -0.68
     spaniel
    -0.65
     HasFactory
    -0.65
    ,:);
    -0.65
    CppCodeGen
    -0.63
    openConnection
    -0.62
    matchCondition
    -0.62
    Geplaatst
    -0.61
    fhir
    -0.61
    POSITIVE LOGITS
     that
    0.65
     bahawa
    0.48
     bahwa
    0.46
     there
    0.46
    RuleContext
    0.45
     plă
    0.43
     fallu
    0.43
    CJK
    0.43
     gauche
    0.41
    kiel
    0.41
    Act Density 0.195%

    No Known Activations