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

    Neuronpedia

    INDEX
    Explanations

    text related to a specific topic or subject

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific topic or subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERROR
    -0.71
     Zimmer
    -0.69
     fortune
    -0.67
    aukee
    -0.66
    Ka
    -0.66
    ATES
    -0.66
    GBT
    -0.63
    Cop
    -0.63
    ereo
    -0.63
    IELD
    -0.62
    POSITIVE LOGITS
    matter
    1.17
    ivity
    1.15
    ively
    1.10
    ivist
    1.02
    ivities
    1.02
    itatively
    0.95
    ivism
    0.93
    userc
    0.93
    icals
    0.91
     matter
    0.90
    Act Density 0.015%

    No Known Activations