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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opposing viewpoints or controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    xus
    -0.89
    frac
    -0.73
     Caption
    -0.72
    kamp
    -0.70
    ilit
    -0.69
    uez
    -0.68
    ventus
    -0.66
    nect
    -0.65
    renheit
    -0.64
    idation
    -0.64
    POSITIVE LOGITS
     sexes
    1.41
     genders
    1.18
     sides
    1.17
     halves
    0.92
     domestically
    0.82
     orally
    0.81
     verbally
    0.80
     individually
    0.74
     internally
    0.74
     anecd
    0.71
    Act Density 0.045%

    No Known Activations