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

    Neuronpedia

    INDEX
    Explanations

    keywords related to other people or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to "others" and their experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Url
    -0.62
    OA
    -0.61
    ultimate
    -0.60
    glers
    -0.57
     Hulk
    -0.57
     Kamp
    -0.57
     Warlock
    -0.57
    Sac
    -0.57
    Nin
    -0.56
    Lock
    -0.56
    POSITIVE LOGITS
    paces
    1.11
     who
    1.00
    worldly
    0.96
     besides
    0.86
     else
    0.84
     involved
    0.83
     like
    0.77
     alike
    0.77
    who
    0.75
     whom
    0.75
    Act Density 0.062%

    No Known Activations