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

    Neuronpedia

    INDEX
    Explanations

    phrases related to confinement or restriction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to confinement and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Authors
    -0.70
    llo
    -0.68
    alis
    -0.68
    ulia
    -0.68
    opoulos
    -0.66
     choir
    -0.65
    eli
    -0.64
    orks
    -0.62
    itia
    -0.61
     uproar
    -0.61
    POSITIVE LOGITS
     Borders
    0.84
    hold
    0.78
     leash
    0.76
    loader
    0.75
    posts
    0.71
     borders
    0.68
    rency
    0.68
    ainers
    0.67
     desks
    0.65
    road
    0.65
    Act Density 0.132%

    No Known Activations