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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sanctions or restricted/prohibited items/people/activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sanctuary cities and online communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kingdoms
    -0.75
    REE
    -0.72
     Disp
    -0.68
     Scand
    -0.67
    sg
    -0.63
    ython
    -0.62
    ANY
    -0.61
     Rocks
    -0.61
     Lunar
    -0.59
    ï¸ı
    -0.59
    POSITIVE LOGITS
    ctuary
    1.03
    ufact
    1.01
    ovic
    0.91
    ews
    0.90
    esthetic
    0.90
    nered
    0.90
    quez
    0.87
    abilia
    0.84
    thood
    0.84
    onymous
    0.84
    Act Density 0.034%

    No Known Activations