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

    Neuronpedia

    INDEX
    Explanations

    words related to a starting point or origin

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating starting or turning points in discussions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uthor
    -0.99
    pload
    -0.91
    apons
    -0.86
    ãĥīãĥ©
    -0.71
     Klux
    -0.69
    unte
    -0.68
     pancakes
    -0.67
    iverpool
    -0.66
    estic
    -0.66
    itte
    -0.65
    POSITIVE LOGITS
    points
    0.90
    imus
    0.82
    point
    0.80
    pointers
    0.73
    ifiers
    0.73
    ifier
    0.72
    lessly
    0.72
    edly
    0.71
    ansas
    0.69
     Gemini
    0.67
    Act Density 0.030%

    No Known Activations