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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and questioning motivations or feelings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     HOUSING
    -0.52
     /^[
    -0.50
     indeed
    -0.49
     scénario
    -0.49
     novel
    -0.48
    sprüng
    -0.47
     nitrogen
    -0.47
     hmot
    -0.47
    之下
    -0.47
    izhou
    -0.47
    POSITIVE LOGITS
    Personensuche
    0.87
    yntaxException
    0.84
     ModelExpression
    0.80
    InjectAttribute
    0.80
     EconPapers
    0.79
    tanleria
    0.77
    SourceChecksum
    0.77
    исленность
    0.76
    Somehow
    0.75
    protoimpl
    0.75
    Act Density 0.081%

    No Known Activations