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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical restraint and coercion

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to choking and restraint

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    finder
    -0.75
    Ô
    -0.73
    estate
    -0.70
    onymous
    -0.69
     Destination
    -0.69
    atican
    -0.66
    hof
    -0.66
     Scotia
    -0.65
    onym
    -0.65
    nings
    -0.64
    POSITIVE LOGITS
    hold
    0.99
     confinement
    0.91
     breathing
    0.88
     shack
    0.87
     leash
    0.84
     restrain
    0.83
     choking
    0.82
     wrists
    0.81
     waist
    0.80
     clinging
    0.78
    Act Density 0.146%

    No Known Activations