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

    Neuronpedia

    INDEX
    Explanations

    instances where information related to the public is discussed or mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to the public and public interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Scroll
    -0.74
    YP
    -0.70
    pread
    -0.70
    imov
    -0.69
    eton
    -0.68
    phy
    -0.67
    wered
    -0.67
    kson
    -0.67
    ihad
    -0.67
    Pg
    -0.66
    POSITIVE LOGITS
     purse
    1.01
     outcry
    0.98
     sector
    0.96
     servants
    0.92
     sphere
    0.92
     broadcaster
    0.91
     perception
    0.88
     domain
    0.83
    eye
    0.82
     servant
    0.79
    Act Density 0.050%

    No Known Activations