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

    Neuronpedia

    INDEX
    Explanations

    words indicating strong emotions or significant experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    959
    -0.14
    yun
    -0.14
    ább
    -0.14
     Duy
    -0.14
    cha
    -0.14
    Åĵ
    -0.13
     Emm
    -0.13
    æĿij
    -0.13
    umba
    -0.13
     hardware
    -0.13
    POSITIVE LOGITS
    orners
    0.16
    argas
    0.15
    oka
    0.15
    toHave
    0.15
    евид
    0.14
    exchange
    0.14
    .usage
    0.14
    Extras
    0.14
    .cod
    0.13
     Exchange
    0.13
    Act Density 0.018%

    No Known Activations