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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating the progression of events

    oai_token-act-pair · gpt-3.5-turbo

    words indicating time-related sequences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulence
    -0.73
    inav
    -0.73
    yip
    -0.71
    lag
    -0.71
    oes
    -0.70
    onian
    -0.69
    ERAL
    -0.68
    regate
    -0.67
    ogun
    -0.67
    idem
    -0.67
    POSITIVE LOGITS
     thrown
    1.06
     photographed
    1.06
     subjected
    1.04
     able
    1.02
     supposed
    1.00
     mistaken
    1.00
     tasked
    0.99
     notified
    0.97
     rewarded
    0.96
     taken
    0.95
    Act Density 0.127%

    No Known Activations