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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating permission or encouragement to proceed with an action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progression or taking action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥µ
    -0.67
    brid
    -0.66
    ingham
    -0.66
    asio
    -0.65
    ELD
    -0.63
    igi
    -0.62
    GAME
    -0.62
    NET
    -0.62
    rador
    -0.61
     Comput
    -0.61
    POSITIVE LOGITS
    nesses
    0.75
    eous
    0.73
     unnoticed
    0.73
    lems
    0.69
     undet
    0.68
     anyway
    0.67
    acht
    0.62
    estyles
    0.62
    nah
    0.61
    abouts
    0.61
    Act Density 0.030%

    No Known Activations