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

    Neuronpedia

    INDEX
    Explanations

    references to poverty or poor quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding adjectives, often positive

    np_acts-logits-general · gemini-2.0-flash

    good old dear plain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.68
    Personensuche
    -0.67
    <bos>
    -0.63
    AnchorStyles
    -0.63
    SharedDtor
    -0.63
    addCriterion
    -0.60
     ExecuteAsync
    -0.60
     ligiloj
    -0.59
    intios
    -0.56
    writeFieldEnd
    -0.54
    POSITIVE LOGITS
     old
    1.54
     ol
    1.27
     trusty
    1.22
     gamle
    1.20
     viejos
    1.16
     vieille
    1.14
     vieux
    1.14
     gamla
    1.13
     vieilles
    1.13
     vecchio
    1.10
    Act Density 0.168%

    No Known Activations