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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal restrictions or prohibitions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to restrictions or prohibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.87
    ¯¯
    -0.80
    DERR
    -0.74
    Champ
    -0.70
    ¯
    -0.70
    ACT
    -0.70
    ¯¯¯¯
    -0.70
    gaard
    -0.68
    é¾įåĸļ士
    -0.66
    OGR
    -0.66
    POSITIVE LOGITS
    erous
    1.32
     behalf
    0.94
     sale
    0.79
     restricting
    0.78
    shore
    0.75
     regulating
    0.73
     preserving
    0.72
    etheless
    0.72
     preventing
    0.72
     prohibiting
    0.72
    Act Density 0.098%

    No Known Activations