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

    Neuronpedia

    INDEX
    Explanations

    specific food-related terminology and concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     though
    -0.86
     but
    -0.82
     however
    -0.75
    ,
    -0.71
     aber
    -0.67
     entanto
    -0.64
    though
    -0.63
     nhưng
    -0.63
    になりますが
    -0.62
    ですが
    -0.62
    POSITIVE LOGITS
     Reſ
    0.87
     Houſe
    0.84
     Theſe
    0.83
     Diſ
    0.82
     itſelf
    0.82
     فريبيس
    0.81
     Majefty
    0.80
     виправивши
    0.80
     AssemblyCulture
    0.77
     ainfi
    0.77
    Act Density 1.005%

    No Known Activations