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

    Neuronpedia

    INDEX
    Explanations

    academic terms or scholarly content

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bundy
    -0.80
    ACTED
    -0.71
    generic
    -0.71
    xon
    -0.69
    rays
    -0.67
    coni
    -0.67
    lessly
    -0.66
    woods
    -0.66
    zik
    -0.66
    lua
    -0.65
    POSITIVE LOGITS
    ulty
    0.93
     institutions
    0.93
     disciplines
    0.92
    essors
    0.88
    ademic
    0.88
     faculty
    0.87
     attainment
    0.85
     academic
    0.84
     dean
    0.82
     achie
    0.82
    Act Density 0.026%

    No Known Activations