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

    Neuronpedia

    INDEX
    Explanations

    mentions of the breed "pit bull"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "pit bulls."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.68
     Lauder
    -0.66
     Feinstein
    -0.61
    e
    -0.59
     Polo
    -0.59
    ë
    -0.58
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.58
    Pacific
    -0.57
     XD
    -0.57
     commons
    -0.57
    POSITIVE LOGITS
    iful
    1.51
    cair
    1.41
    iless
    1.40
    ifully
    1.37
    bull
    1.26
    cher
    1.23
    chers
    1.00
    uit
    0.99
    iable
    0.98
     bulls
    0.97
    Act Density 0.036%

    No Known Activations