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

    Neuronpedia

    INDEX
    Explanations

    references to places of detention, particularly jails

    oai_token-act-pair · gpt-3.5-turbo

    references to jails or imprisonment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nare
    -0.79
    FORE
    -0.73
    yip
    -0.73
     Scotia
    -0.72
     Bundes
    -0.69
    xit
    -0.67
    chell
    -0.65
     livest
    -0.63
    ndum
    -0.63
    ilater
    -0.63
    POSITIVE LOGITS
    breaks
    0.85
    broken
    0.85
    break
    0.85
    strap
    0.85
    rooms
    0.84
    house
    0.82
    breakers
    0.80
     jails
    0.78
    itory
    0.77
     jail
    0.76
    Act Density 0.019%

    No Known Activations