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

    Neuronpedia

    INDEX
    Explanations

    words containing the specific substring "unw"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of being unrestrained or lacking boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onyms
    -0.84
    anwhile
    -0.79
    milo
    -0.71
    oples
    -0.69
    cium
    -0.67
     Spray
    -0.65
    uyomi
    -0.65
    ggle
    -0.63
    ĺħ
    -0.62
    ften
    -0.62
    POSITIVE LOGITS
    ritten
    1.05
    inding
    1.00
    arranted
    0.95
    ield
    0.86
    ashed
    0.84
    ashington
    0.83
    Connell
    0.83
    irth
    0.80
     unw
    0.80
    aii
    0.77
    Act Density 0.006%

    No Known Activations