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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or entities

    oai_token-act-pair · gpt-3.5-turbo

    names of organizations, people, and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.74
    åĤ
    -0.66
    ploma
    -0.65
    existent
    -0.64
    incarn
    -0.63
     curve
    -0.61
    insula
    -0.61
    cise
    -0.60
    Ö¼
    -0.60
    Ö
    -0.58
    POSITIVE LOGITS
     reverted
    0.69
     programmers
    0.68
     spokesman
    0.64
     spokeswoman
    0.64
     wrote
    0.64
    udos
    0.63
     analysts
    0.62
    lett
    0.61
     engineers
    0.61
     vowed
    0.61
    Act Density 0.389%

    No Known Activations