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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules, regulation, and prohibition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restrictions or bans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eah
    -0.81
    eon
    -0.74
    neau
    -0.68
    visors
    -0.68
     Norn
    -0.67
    etics
    -0.67
    prise
    -0.66
    igma
    -0.66
    itched
    -0.66
    tone
    -0.66
    POSITIVE LOGITS
     prohibited
    0.80
    bidden
    0.77
     forbids
    0.76
     prohibition
    0.76
     nudity
    0.76
     substances
    0.74
     interfere
    0.73
    dylib
    0.72
     forbidden
    0.72
     prohibit
    0.71
    Act Density 0.053%

    No Known Activations