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

    Neuronpedia

    INDEX
    Explanations

    various vocal sounds and exclamations

    oai_token-act-pair · gpt-3.5-turbo

    instances of end-of-text markers or non-standard text patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prospect
    -0.72
     Redux
    -0.66
     Strauss
    -0.63
     Associates
    -0.63
     exerc
    -0.62
    actionDate
    -0.61
     substitution
    -0.60
     Hasan
    -0.59
     JPM
    -0.59
     compass
    -0.59
    POSITIVE LOGITS
    ooo
    1.12
    oooo
    1.11
    mmmm
    1.08
    aaaa
    1.04
    AAAA
    0.99
    mmm
    0.99
    OOOO
    0.97
    hhh
    0.97
    !!!!!
    0.95
     kidding
    0.95
    Act Density 0.172%

    No Known Activations