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

    Neuronpedia

    INDEX
    Explanations

    phrases related to imprisonment or confinement

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing confinement or restriction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gomery
    -0.78
    alis
    -0.76
    CAST
    -0.69
    JC
    -0.69
    eni
    -0.68
    LL
    -0.68
    enegger
    -0.67
    eli
    -0.66
    lez
    -0.64
    llo
    -0.64
    POSITIVE LOGITS
    hold
    0.80
     Borders
    0.75
    posts
    0.72
     knots
    0.71
    bed
    0.70
    reements
    0.69
     leash
    0.67
     resists
    0.67
    ainers
    0.66
     tightly
    0.64
    Act Density 0.108%

    No Known Activations