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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing preferences or desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (&:
    -0.72
     Berman
    -0.70
    olus
    -0.63
     سبيل
    -0.62
    se
    -0.61
     Barrera
    -0.60
    ResourceBundle
    -0.60
     Bowman
    -0.58
    upta
    -0.58
    </h3>
    -0.58
    POSITIVE LOGITS
    évaluateur
    0.86
     Niv
    0.76
     guste
    0.74
     gustaría
    0.73
    avoit
    0.70
    jalá
    0.67
    reciate
    0.66
     pedic
    0.63
     involuc
    0.63
    ARTICLE
    0.63
    Act Density 0.040%

    No Known Activations