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

    Neuronpedia

    INDEX
    Explanations

    references to academic professors

    oai_token-act-pair · gpt-3.5-turbo

    references to academic titles, specifically "professor."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sled
    -0.72
    axy
    -0.70
    ãĥ¼ãĥ³
    -0.64
     territ
    -0.63
     Pradesh
    -0.63
    adies
    -0.63
    tera
    -0.62
     Devils
    -0.62
    opter
    -0.61
    ntax
    -0.61
    POSITIVE LOGITS
    essors
    1.06
    ials
    0.95
     emer
    0.94
    ially
    0.93
    iate
    0.92
    essor
    0.88
    icist
    0.86
    itatively
    0.85
    ertation
    0.83
    hesis
    0.81
    Act Density 0.018%

    No Known Activations