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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cause and effect

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causation or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yahoo
    -0.64
    holder
    -0.64
    ura
    -0.63
    ahs
    -0.63
    ath
    -0.62
    anon
    -0.60
    oss
    -0.60
    zon
    -0.60
    mins
    -0.59
    aru
    -0.59
    POSITIVE LOGITS
     partly
    1.07
     solely
    0.89
     chiefly
    0.88
     partially
    0.79
     disproportionately
    0.79
     factors
    0.78
     principally
    0.78
     exacerbated
    0.76
     largely
    0.76
     entirely
    0.76
    Act Density 0.208%

    No Known Activations