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

    Neuronpedia

    INDEX
    Explanations

    statements about quantitative assessments and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.59
    󠁴
    -0.55
    řevě
    -0.50
    invokeLater
    -0.49
     bypass
    -0.48
     simples
    -0.48
    dafx
    -0.48
    CreateMap
    -0.48
    ंदीखरीदारी
    -0.47
     invokingState
    -0.47
    POSITIVE LOGITS
     peanuts
    0.66
     impressive
    0.60
    EndContext
    0.59
    脚注の使い方
    0.59
     generous
    0.58
     excessive
    0.57
     Wikimédia
    0.56
    stantial
    0.56
     respectable
    0.56
    Plenty
    0.56
    Act Density 0.450%

    No Known Activations