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

    Neuronpedia

    INDEX
    Explanations

    expressions related to achievement or completion

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement or intensity related to enjoyment and satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    foreseen
    -0.73
    inese
    -0.73
    emouth
    -0.65
    inement
    -0.64
    uese
    -0.64
    objects
    -0.62
    working
    -0.62
     intimate
    -0.61
    itamin
    -0.61
     unfamiliar
    -0.60
    POSITIVE LOGITS
     prest
    1.01
     vo
    0.69
     Bye
    0.68
     Rut
    0.68
    bye
    0.68
    opter
    0.66
     vanquished
    0.66
    ILA
    0.65
     prevailed
    0.64
    Ô
    0.64
    Act Density 0.612%

    No Known Activations