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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to visual appearance and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to appearances and perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oute
    -0.67
    oulos
    -0.66
    cember
    -0.62
     railing
    -0.60
    ciating
    -0.60
     Strikes
    -0.60
     Perspect
    -0.60
     Variant
    -0.60
     Ways
    -0.59
     ensu
    -0.59
    POSITIVE LOGITS
     stronger
    0.84
     nicer
    0.80
     invincible
    0.79
     bigger
    0.79
     attractive
    0.78
     smarter
    0.78
     insignificant
    0.77
    thood
    0.76
     weaker
    0.75
     worse
    0.74
    Act Density 0.109%

    No Known Activations