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

    Neuronpedia

    INDEX
    Explanations

    references to legal situations and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enfans
    -0.67
     المعيارى
    -0.56
    .
    -0.56
     hunne
    -0.55
     فريبيس
    -0.51
     figliu
    -0.51
     חיצוניים
    -0.49
    ServiceModel
    -0.48
     serem
    -0.48
     bambina
    -0.48
    POSITIVE LOGITS
     inoltre
    1.02
     however
    0.97
     therefore
    0.96
     also
    0.91
     entanto
    0.84
    however
    0.80
    '},
    0.79
    WriteBarrier
    0.74
    Jereo
    0.71
     natomiast
    0.71
    Act Density 6.109%

    No Known Activations