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

    Neuronpedia

    INDEX
    Explanations

    time-related events or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of temporal markers or phrases indicating time and context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     etc
    -0.78
     ðŁĻĤ
    -0.68
     darn
    -0.68
     Nope
    -0.67
     eternal
    -0.67
     EVERY
    -0.66
     eternity
    -0.65
     Annotations
    -0.65
     thereof
    -0.65
     NEVER
    -0.64
    POSITIVE LOGITS
    resa
    1.12
    ogether
    0.96
    iday
    0.94
    odore
    0.92
    xiety
    0.87
    nsic
    0.84
    alyst
    0.84
    respond
    0.83
    intendent
    0.80
    wards
    0.79
    Act Density 0.364%

    No Known Activations