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

    Neuronpedia

    INDEX
    Explanations

    violent and intense actions

    oai_token-act-pair · gpt-3.5-turbo

    significant events or actions related to conflict and struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     culp
    -0.60
     Psych
    -0.60
     Paran
    -0.60
     Spoiler
    -0.59
     Canad
    -0.54
     Yon
    -0.54
     Chili
    -0.53
    ãĥ³ãĤ¸
    -0.53
     Aerospace
    -0.52
     Masonic
    -0.52
    POSITIVE LOGITS
    bearing
    0.81
    queue
    0.74
    seekers
    0.71
    until
    0.69
    TPS
    0.69
    ttes
    0.65
    æĸ¹
    0.64
    ãĢĤ
    0.64
    levels
    0.62
    worm
    0.62
    Act Density 1.244%

    No Known Activations