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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iframe
    -0.69
    selves
    -0.68
    lly
    -0.66
    stuff
    -0.61
    voice
    -0.61
    emo
    -0.61
    pointers
    -0.60
    lot
    -0.60
     rejoice
    -0.59
    uces
    -0.59
    POSITIVE LOGITS
     captivity
    1.36
     prison
    1.19
    prison
    1.11
    patient
    1.06
     jail
    0.99
     isolation
    0.98
     custody
    0.97
     exile
    0.96
     remission
    0.93
    activity
    0.93
    Act Density 0.081%

    No Known Activations