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

    Neuronpedia

    INDEX
    Explanations

    words related to medical issues and problems

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ore."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srf
    -0.76
    otaur
    -0.75
    ilts
    -0.74
    keye
    -0.72
    ulk
    -0.71
    keyes
    -0.70
    insula
    -0.69
    cellence
    -0.68
     ILCS
    -0.67
    cffff
    -0.67
    POSITIVE LOGITS
    tto
    1.26
    tsky
    1.16
    gon
    1.14
    lli
    1.07
    cki
    0.95
    tta
    0.95
    ttes
    0.94
    llo
    0.93
    nz
    0.92
    xia
    0.91
    Act Density 0.014%

    No Known Activations