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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating some kind of capability or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating capability or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Technique
    -0.73
     Tradition
    -0.71
     Deer
    -0.70
     Alone
    -0.64
     Philips
    -0.64
     Parents
    -0.62
     Mother
    -0.61
     Param
    -0.61
     Doct
    -0.61
     Caval
    -0.60
    POSITIVE LOGITS
    bodied
    1.03
    ioned
    0.97
    reys
    0.93
    't
    0.79
    llor
    0.76
     traged
    0.76
    anooga
    0.75
    ittees
    0.74
     access
    0.74
    Enlarge
    0.74
    Act Density 0.031%

    No Known Activations