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

    Neuronpedia

    INDEX
    Explanations

    phrases with unusual characters like accents, tildes, or symbols

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to creative titles or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lapse
    -0.89
     condem
    -0.80
     pressures
    -0.79
     conduc
    -0.76
     limb
    -0.72
     assum
    -0.72
     draw
    -0.71
     dismiss
    -0.71
     frust
    -0.71
     ways
    -0.71
    POSITIVE LOGITS
    ï¸ı
    1.18
    Operation
    1.11
    cffffcc
    1.05
    É
    1.01
    _>
    1.00
    STAR
    1.00
    Torrent
    0.99
    ×Ķ
    0.95
    $
    0.93
    mega
    0.93
    Act Density 0.171%

    No Known Activations