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

    Neuronpedia

    INDEX
    Explanations

    words related to units of data storage or computational power

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ter" and related variations indicating intensity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooth
    -0.78
    emi
    -0.76
    hiro
    -0.76
    EGA
    -0.71
    »Ĵ
    -0.70
    oresc
    -0.69
    OWN
    -0.68
     Shiv
    -0.65
     DeV
    -0.65
    Ĭ±
    -0.64
    POSITIVE LOGITS
    ciating
    0.86
    pher
    0.83
    mic
    0.82
    args
    0.79
    TY
    0.77
    riers
    0.76
    iously
    0.75
    notations
    0.75
    ping
    0.74
    abytes
    0.74
    Act Density 0.056%

    No Known Activations