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

    Neuronpedia

    INDEX
    Explanations

    dates or specific time-related events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating specific incidents or timelines of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.74
    Lean
    -0.73
    ©¶æ¥µ
    -0.72
    ãĤ§
    -0.69
    thood
    -0.68
    ascus
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    ongyang
    -0.65
    AppData
    -0.65
    igr
    -0.65
    POSITIVE LOGITS
     assailants
    0.83
     protesters
    0.81
     protestors
    0.80
     contestants
    0.77
     protester
    0.76
     combatants
    0.75
     bystanders
    0.74
     gunmen
    0.74
     demonstrators
    0.72
     participants
    0.72
    Act Density 0.641%

    No Known Activations