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

    Neuronpedia

    INDEX
    Explanations

    words related to impolite behavior or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to rudeness and impolite behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iphate
    -0.86
    ernels
    -0.84
    20439
    -0.84
    ilation
    -0.82
    arijuana
    -0.80
    Downloadha
    -0.75
    assies
    -0.74
    inoa
    -0.74
    akings
    -0.74
    iverpool
    -0.73
    POSITIVE LOGITS
     rude
    1.19
     awakening
    1.03
     rud
    0.87
    ly
    0.85
     manners
    0.83
    soever
    0.82
    ãģį
    0.77
     jerk
    0.75
    ¾
    0.75
     boun
    0.74
    Act Density 0.010%

    No Known Activations