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

    Neuronpedia

    INDEX
    Explanations

    keywords related to legality, propriety, and prudence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to propriety and appropriate behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carrier
    -0.71
     Ribbon
    -0.69
     Haskell
    -0.66
     bay
    -0.66
     beetle
    -0.65
     Medals
    -0.64
    ware
    -0.63
     Luther
    -0.63
     prisoner
    -0.63
     Glob
    -0.63
    POSITIVE LOGITS
    ropri
    1.18
    ety
    1.01
    orrow
    1.00
    cious
    0.99
    kefeller
    0.96
    oir
    0.95
    eous
    0.92
    odcast
    0.91
    zzo
    0.90
    yright
    0.88
    Act Density 0.027%

    No Known Activations