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

    Neuronpedia

    INDEX
    Explanations

    words related to dissatisfaction or unsatisfactory situations

    oai_token-act-pair · gpt-3.5-turbo

    words related to dissatisfaction and beauty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.79
     Goddard
    -0.67
     Birch
    -0.66
     Sapphire
    -0.65
    anwhile
    -0.63
     Bore
    -0.63
    PRESS
    -0.63
    uberty
    -0.62
     Dres
    -0.62
    ffer
    -0.61
    POSITIVE LOGITS
    icion
    1.03
    ications
    0.92
    ying
    0.91
     unden
    0.89
    ¡
    0.89
    ifully
    0.87
    icio
    0.86
    iful
    0.85
     pse
    0.85
    inav
    0.85
    Act Density 0.026%

    No Known Activations