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

    Neuronpedia

    INDEX
    Explanations

    mentions of the location "Siberia."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "oria" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ned
    -0.76
    ulating
    -0.74
    words
    -0.72
    eworld
    -0.72
    keye
    -0.71
    books
    -0.71
    keyes
    -0.69
    lining
    -0.68
    esar
    -0.66
    lishes
    -0.66
    POSITIVE LOGITS
     Adin
    0.87
    andom
    0.84
     XIII
    0.75
    tsky
    0.72
    APH
    0.72
    llo
    0.69
    ||||
    0.69
    ROR
    0.67
     Jarrett
    0.67
    ETHOD
    0.66
    Act Density 0.046%

    No Known Activations