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

    Neuronpedia

    INDEX
    Explanations

    references to scholars and their associated actions or attributes

    oai_token-act-pair · gpt-3.5-turbo

    references to academics or individuals engaged in scholarly work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PID
    -0.77
    Switch
    -0.72
     Hazard
    -0.69
     GoPro
    -0.69
    liquid
    -0.69
     Bravo
    -0.69
     Liquid
    -0.68
    shot
    -0.67
     RC
    -0.66
    outine
    -0.66
    POSITIVE LOGITS
     scholars
    3.31
     scholar
    3.15
     Scholars
    2.51
     Scholar
    2.35
     scholarly
    2.16
     scholarship
    2.08
     academics
    1.81
     historians
    1.69
     professors
    1.57
     Scholarship
    1.54
    Act Density 0.022%

    No Known Activations