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

    Neuronpedia

    INDEX
    Explanations

    references to being in jail or facing imprisonment

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to incarceration and imprisonment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plurality
    -0.69
    ulner
    -0.65
    quart
    -0.64
    onal
    -0.64
    ween
    -0.63
    ophe
    -0.62
    rex
    -0.62
    cific
    -0.61
    ombs
    -0.61
    ript
    -0.60
    POSITIVE LOGITS
     limbo
    0.72
     Reloaded
    0.70
     ..........
    0.69
    pedia
    0.69
     hearings
    0.68
    Ø©
    0.66
     awaiting
    0.64
     proceedings
    0.61
     Hearing
    0.59
     dehydration
    0.59
    Act Density 0.077%

    No Known Activations