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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    oai_token-act-pair · gpt-3.5-turbo

    temporal markers indicating specific days or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geries
    -0.76
     spoiler
    -0.68
     eg
    -0.67
    origin
    -0.63
    gery
    -0.62
    Ly
    -0.60
     Enchant
    -0.58
     gib
    -0.58
     continuity
    -0.57
    harm
    -0.57
    POSITIVE LOGITS
     reacted
    0.96
     dismiss
    0.87
     launched
    0.86
     opted
    0.85
     accuse
    0.85
     undertook
    0.84
     unveiled
    0.84
     urged
    0.84
     announced
    0.84
     withdrew
    0.83
    Act Density 0.156%

    No Known Activations