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

    Neuronpedia

    INDEX
    Explanations

    phrases related to planning or organization

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to policy implications and judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennett
    -0.63
    addon
    -0.60
    ials
    -0.59
    arter
    -0.58
     ><
    -0.55
    rison
    -0.52
    ainers
    -0.49
    ants
    -0.48
     Serpent
    -0.48
    antics
    -0.48
    POSITIVE LOGITS
     incidentally
    0.57
     belonged
    0.57
    Els
    0.56
     antit
    0.56
     Euros
    0.55
     resembled
    0.52
    fit
    0.52
     outwe
    0.50
    é¾įå¥ij士
    0.49
     outweigh
    0.49
    Act Density 0.718%

    No Known Activations