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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and entities

    oai_token-act-pair · gpt-3.5-turbo

    specific names, titles, and organizations associated with notable subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.84
    soever
    -0.75
    Merit
    -0.72
    ordable
    -0.71
    erred
    -0.68
    rador
    -0.67
     "$:/
    -0.66
    soType
    -0.65
    ortment
    -0.63
    posure
    -0.58
    POSITIVE LOGITS
    pedia
    0.96
     FAQ
    0.84
    HQ
    0.73
     creator
    0.70
     enthusiast
    0.69
    icist
    0.69
    forum
    0.69
     proponent
    0.67
     historian
    0.66
     cz
    0.65
    Act Density 0.895%

    No Known Activations