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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to specific individuals and companies

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names associated with individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.80
     Samoa
    -0.80
    eering
    -0.79
    ividual
    -0.76
    IBLE
    -0.74
     à¨
    -0.73
     defe
    -0.72
    ially
    -0.72
    ãĤ¨ãĥ«
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.71
    POSITIVE LOGITS
    stre
    0.97
    acher
    0.91
    bs
    0.85
    Vert
    0.84
    ffer
    0.84
    mer
    0.83
    ven
    0.82
    pton
    0.82
    utz
    0.82
    pps
    0.81
    Act Density 0.013%

    No Known Activations