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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusivity or singling out

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    insula
    -0.73
    ahime
    -0.71
     heterogeneity
    -0.69
    illin
    -0.65
    ulty
    -0.64
    idon
    -0.63
    arted
    -0.63
    raught
    -0.62
     charism
    -0.61
    anon
    -0.61
    POSITIVE LOGITS
     marginally
    1.10
    ICES
    0.93
    ices
    0.92
     kidding
    0.86
    ĨĴ
    0.86
     incidentally
    0.83
     spor
    0.81
    £ı
    0.79
     briefly
    0.79
     mildly
    0.75
    Act Density 6.006%

    No Known Activations