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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.75
    UrlResolution
    -0.67
     Wikimedijinoj
    -0.67
     étoient
    -0.66
     avoient
    -0.65
    InjectAttribute
    -0.64
    onAttach
    -0.60
    lapsingToolbar
    -0.60
     parseFrom
    -0.59
     avoit
    -0.58
    POSITIVE LOGITS
     fact
    0.58
     thế
    0.55
     réessayer
    0.53
     μή
    0.53
    тому
    0.52
    ystema
    0.51
     plus
    0.51
     nahilalakip
    0.51
    ularia
    0.51
    …………………………………………
    0.50
    Act Density 0.318%

    No Known Activations