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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and formatting in equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -0.90
     Majefty
    -0.88
     reaſon
    -0.87
     poffible
    -0.87
     pleaſure
    -0.87
     Monfieur
    -0.86
     Theſe
    -0.84
     fevere
    -0.83
     Jefus
    -0.83
     myſelf
    -0.82
    POSITIVE LOGITS
     таки
    0.53
     noqa
    0.51
    éndole
    0.51
    θρώ
    0.51
    biendo
    0.50
    grimas
    0.50
     lev
    0.49
    ksanakan
    0.46
     CanadaChoose
    0.46
     Mal
    0.45
    Act Density 0.385%

    No Known Activations