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

    Neuronpedia

    INDEX
    Explanations

    verbs related to interpersonal dynamics and interactions

    oai_token-act-pair · gpt-3.5-turbo

    themes related to self-perception and societal judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.71
    rolet
    -0.66
     earthqu
    -0.65
    aceutical
    -0.59
     Budget
    -0.57
     Solitaire
    -0.57
     Launcher
    -0.57
    WORK
    -0.56
    starter
    -0.55
     Playoffs
    -0.55
    POSITIVE LOGITS
     themselves
    1.31
     them
    1.30
     oneself
    1.27
     him
    1.15
     herself
    1.07
    him
    1.06
     others
    1.05
     their
    1.03
     himself
    1.02
     theirs
    1.02
    Act Density 0.312%

    No Known Activations