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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussions or debates

    oai_token-act-pair · gpt-3.5-turbo

    discussions and mentions of various topics in public discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPS
    -0.69
    0000000000000000
    -0.64
    asar
    -0.62
    oration
    -0.62
    UME
    -0.62
    GROUP
    -0.62
    66666666
    -0.61
     Osc
    -0.61
     Takeru
    -0.59
    BP
    -0.59
    POSITIVE LOGITS
     countless
    0.91
     lately
    0.85
     numerous
    0.78
     extensively
    0.77
    buquerque
    0.73
     philosophers
    0.73
     innumerable
    0.70
     anecd
    0.66
    ¥ŀ
    0.66
     advoc
    0.65
    Act Density 1.345%

    No Known Activations