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

    Neuronpedia

    INDEX
    Explanations

    terms related to various fields of science and academic disciplines

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    leased
    -0.70
    fman
    -0.69
    izen
    -0.65
    ishers
    -0.64
    estead
    -0.62
    este
    -0.61
    fires
    -0.61
    inel
    -0.61
    gotten
    -0.59
    achable
    -0.59
    POSITIVE LOGITS
    utics
    0.96
     textbooks
    0.95
     professor
    0.92
    ology
    0.86
    istry
    0.86
    chool
    0.83
    ologies
    0.79
    biology
    0.77
    mith
    0.77
     textbook
    0.76
    Act Density 0.128%

    No Known Activations