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

    Neuronpedia

    INDEX
    Explanations

    names or similar short specific words related to people

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of variations of the word "dude."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olulu
    -0.82
    marked
    -0.81
    ãĥ£
    -0.81
     ILCS
    -0.79
    awaru
    -0.77
    stall
    -0.76
    pora
    -0.76
    Interstitial
    -0.76
    redits
    -0.72
    erald
    -0.72
    POSITIVE LOGITS
    lder
    0.82
    geries
    0.82
    uces
    0.80
    geist
    0.74
    udes
    0.73
    xual
    0.73
    icone
    0.70
    llers
    0.70
    ude
    0.68
    gom
    0.66
    Act Density 0.025%

    No Known Activations