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

    Neuronpedia

    INDEX
    Explanations

    details related to ongoing or upcoming projects or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicative of ongoing projects or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bucks
    -0.72
     Roots
    -0.70
     Benefits
    -0.69
    iberal
    -0.68
    illet
    -0.66
    joined
    -0.64
    BILL
    -0.64
     Glas
    -0.61
     Reverse
    -0.61
    righteous
    -0.61
    POSITIVE LOGITS
     unsure
    1.18
     unclear
    1.13
     uncertainties
    1.11
     speculative
    1.10
     TBD
    1.06
     unknown
    1.05
     uncertain
    1.05
     undecided
    1.01
     uncertainty
    1.00
     unanswered
    0.98
    Act Density 0.506%

    No Known Activations