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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names related to various topics or entities

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and groups, particularly in a political or social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.76
    Ħ¢
    -0.71
    }.
    -0.65
    é¾įå
    -0.64
     cort
    -0.64
    Marginal
    -0.63
    ĨĴ
    -0.63
     Brett
    -0.63
     Nir
    -0.63
     ..."
    -0.61
    POSITIVE LOGITS
    escription
    0.74
     differently
    0.73
     chained
    0.69
    actly
    0.64
    clusively
    0.63
     squarely
    0.62
     circled
    0.62
     pacing
    0.62
     needing
    0.61
    osite
    0.61
    Act Density 0.762%

    No Known Activations