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

    Neuronpedia

    INDEX
    Explanations

    parenthetical statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses or related punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     footing
    -0.77
     inund
    -0.75
     tackling
    -0.73
     overrun
    -0.73
     overhaul
    -0.73
     overwhelmed
    -0.72
     integ
    -0.72
     drifting
    -0.71
     undet
    -0.71
     crate
    -0.70
    POSITIVE LOGITS
    âĢ¦)
    1.41
    ...)
    1.20
    laughs
    1.15
    emphasis
    1.11
    See
    1.11
    Ironically
    1.09
    hide
    1.08
    Laughs
    1.06
    Also
    1.05
    *)
    1.02
    Act Density 0.047%

    No Known Activations