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

    Neuronpedia

    INDEX
    Explanations

    references to the reader or audience directly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     transfieras
    -0.63
     tantôt
    -0.49
     Offisielt
    -0.49
    InstrumentedTest
    -0.48
    Derbyniad
    -0.48
    IsMutable
    -0.47
    참고
    -0.45
     ModelExpression
    -0.45
    VersionUID
    -0.44
    -0.44
    POSITIVE LOGITS
     ever
    0.75
     truly
    0.61
     compare
    0.60
     haven
    0.57
     plan
    0.57
     want
    0.57
     google
    0.55
     EVER
    0.54
     happen
    0.54
     ask
    0.53
    Act Density 0.144%

    No Known Activations