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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a legal sentence or punishment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to prison sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.82
    ocument
    -0.71
     pse
    -0.67
    VB
    -0.66
     anecd
    -0.62
    izens
    -0.61
    ãĤ¡
    -0.61
     charism
    -0.61
     spontaneously
    -0.61
     dynamically
    -0.60
    POSITIVE LOGITS
     prison
    1.49
    prison
    1.36
     jail
    1.35
     detention
    1.11
     captivity
    1.08
     handcuffs
    1.05
     Prison
    1.01
     hospital
    1.00
     exile
    0.98
     confinement
    0.98
    Act Density 0.045%

    No Known Activations