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

    Neuronpedia

    INDEX
    Explanations

    phrases related to prohibition or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prohibitions or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lycer
    -0.77
    eah
    -0.75
    ammy
    -0.75
    pring
    -0.73
    swick
    -0.72
    etics
    -0.71
    eon
    -0.68
    mond
    -0.67
    yll
    -0.65
    edes
    -0.64
    POSITIVE LOGITS
     smoking
    0.85
     prohibition
    0.81
     nudity
    0.78
    untarily
    0.78
     discrimination
    0.76
    ĸļ
    0.76
     gambling
    0.74
     duplication
    0.72
     tampering
    0.72
     restricting
    0.72
    Act Density 0.062%

    No Known Activations