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

    Neuronpedia

    INDEX
    Explanations

    legal actions and crimes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal charges and convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    humans
    -0.71
     mouths
    -0.65
     migration
    -0.64
    Us
    -0.63
     viewpoints
    -0.63
    Switch
    -0.61
    Exit
    -0.61
    gran
    -0.59
    ugs
    -0.59
     NFC
    -0.58
    POSITIVE LOGITS
    retty
    0.83
    ĸļ
    0.75
     aback
    0.74
    terday
    0.71
    Ļ½
    0.71
    ccording
    0.71
    ļéĨĴ
    0.70
    krit
    0.69
    ¿½
    0.69
     TODAY
    0.69
    Act Density 0.142%

    No Known Activations