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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing the timing and methods of actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the processes and timing of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRE
    -0.64
    KEN
    -0.61
    PORT
    -0.56
     Roller
    -0.56
    ULAR
    -0.55
     Progressive
    -0.55
     Tick
    -0.54
     Dickinson
    -0.54
     444
    -0.53
    ://
    -0.52
    POSITIVE LOGITS
    why
    1.14
     whence
    1.01
     WHY
    0.99
    rogens
    0.99
    where
    0.97
     why
    0.97
     WHERE
    0.94
    how
    0.89
    abouts
    0.88
     where
    0.88
    Act Density 0.056%

    No Known Activations