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

    Neuronpedia

    INDEX
    Explanations

    words related to degeneration, deterioration, and decay

    oai_token-act-pair · gpt-3.5-turbo

    references to degeneration and decay, particularly in a moral or physical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.78
    CHA
    -0.73
    ãĥīãĥ©
    -0.70
     Pillar
    -0.67
    BOOK
    -0.66
    apesh
    -0.66
    AV
    -0.63
    herical
    -0.62
    =-=-=-=-=-=-=-=-
    -0.61
    zza
    -0.59
    POSITIVE LOGITS
    icter
    0.87
    acy
    0.85
     unfocusedRange
    0.81
    gradation
    0.79
     degener
    0.76
    ulent
    0.76
    ation
    0.75
     embr
    0.73
    interstitial
    0.72
    etheless
    0.72
    Act Density 0.008%

    No Known Activations