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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to imprisonment and detention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.67
    ificance
    -0.64
    oughly
    -0.61
     useRouter
    -0.61
    mored
    -0.61
    theon
    -0.60
    ficult
    -0.59
    elemField
    -0.58
     splashed
    -0.57
    wikidata
    -0.57
    POSITIVE LOGITS
    Prison
    0.96
     prisons
    0.94
     prison
    0.88
     Prison
    0.87
     Prisons
    0.86
    prison
    0.84
     prisoners
    0.77
     Jail
    0.76
     jail
    0.75
     inmate
    0.74
    Act Density 0.188%

    No Known Activations