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

    Neuronpedia

    INDEX
    Explanations

    specific actions or restrictions being enforced on individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    words related to restrictions or prohibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.90
    swick
    -0.86
    pring
    -0.74
    lycer
    -0.73
    eon
    -0.68
    itamin
    -0.64
    Bee
    -0.63
    :\
    -0.63
    lings
    -0.62
    Cam
    -0.62
    POSITIVE LOGITS
    ĸļ
    1.03
     nudity
    0.78
     prohibition
    0.76
     discrimination
    0.76
     anyone
    0.76
     unrestricted
    0.75
     exhib
    0.74
     extradition
    0.73
     duplication
    0.73
     enforcement
    0.73
    Act Density 0.041%

    No Known Activations