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

    Neuronpedia

    INDEX
    Explanations

    physical actions involving confrontation or aggression

    oai_token-act-pair · gpt-3.5-turbo

    specific names and identified individuals associated with events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.76
     lawy
    -0.69
     renaissance
    -0.63
    united
    -0.62
    reviewed
    -0.62
     yourselves
    -0.61
    ettlement
    -0.60
     reformed
    -0.59
    DragonMagazine
    -0.58
    Population
    -0.58
    POSITIVE LOGITS
     unconscious
    1.02
    's
    0.95
     kneeling
    0.91
     while
    0.87
     seated
    0.84
     inappropriately
    0.83
     horizontally
    0.82
     whilst
    0.81
    ÃŃs
    0.81
     yelling
    0.80
    Act Density 0.295%

    No Known Activations