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

    Neuronpedia

    INDEX
    Explanations

    phrases related to notable achievements or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     a
    -0.59
    neus
    -0.59
    oldo
    -0.57
     tarko
    -0.57
     two
    -0.55
    يده
    -0.54
     sebuah
    -0.52
     sworn
    -0.52
    Unary
    -0.51
     Fiske
    -0.51
    POSITIVE LOGITS
     المعيارى
    0.93
    paravant
    0.81
    的一些
    0.79
    一些
    0.77
     Himo
    0.75
    )"),
    0.75
     enfance
    0.74
    findall
    0.72
     SOME
    0.72
    Tikang
    0.72
    Act Density 0.105%

    No Known Activations