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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or clauses

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.09
     Chriftian
    -0.88
     ſche
    -0.86
     Efq
    -0.84
     Majefty
    -0.84
     Jefus
    -0.81
     purpoſe
    -0.81
     photolibrary
    -0.80
     Chrif
    -0.79
     juſ
    -0.79
    POSITIVE LOGITS
     Fisch
    0.63
    بات
    0.54
    hastly
    0.52
     бру
    0.52
     بيها
    0.51
    scriptcase
    0.51
    {}{
    0.50
    Kristina
    0.50
     jspb
    0.50
    ECAUSE
    0.50
    Act Density 0.002%

    No Known Activations