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

    Neuronpedia

    INDEX
    Explanations

    future-related concepts and uncertainties

    oai_token-act-pair · gpt-3.5-turbo

    statements and questions about future events and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imar
    -0.63
     "+
    -0.63
    uese
    -0.58
     cumbers
    -0.57
    ushes
    -0.56
     notor
    -0.56
    pict
    -0.55
     actionGroup
    -0.55
     Celest
    -0.55
    rite
    -0.54
    POSITIVE LOGITS
     depends
    1.76
     varies
    1.59
     depended
    1.16
     differs
    1.14
     vary
    1.07
     remains
    1.05
     differed
    1.00
     differ
    1.00
    ?
    0.95
     hinges
    0.91
    Act Density 0.428%

    No Known Activations