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

    Neuronpedia

    INDEX
    Explanations

    news reporting phrases related to current events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate temporal context or sequence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..."
    -0.78
     etc
    -0.75
    .ãĢį
    -0.71
     ______
    -0.67
     ().
    -0.67
    .","
    -0.67
     nipples
    -0.65
     crappy
    -0.64
     \"
    -0.64
     Slayer
    -0.63
    POSITIVE LOGITS
    resa
    1.35
    odore
    1.15
    ogether
    0.97
    romeda
    0.93
    alyst
    0.91
    ccording
    0.87
    xiety
    0.85
    iday
    0.81
    wards
    0.80
    ircraft
    0.79
    Act Density 0.423%

    No Known Activations