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

    Neuronpedia

    INDEX
    Explanations

    phrases related to displaying exceptional strength or dominance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to assertiveness and taking action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forts
    -0.80
    iae
    -0.71
    omnia
    -0.68
    asury
    -0.68
    aucuses
    -0.65
    ukong
    -0.65
     privacy
    -0.64
     pecul
    -0.64
    itizens
    -0.63
    pherd
    -0.63
    POSITIVE LOGITS
     awa
    0.89
     trumpet
    0.72
    arters
    0.68
    BALL
    0.66
    boxing
    0.63
    steen
    0.62
     smack
    0.62
     doors
    0.61
     Unle
    0.61
     admit
    0.61
    Act Density 0.087%

    No Known Activations