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

    Neuronpedia

    INDEX
    Explanations

    tags or metadata

    oai_token-act-pair · gpt-3.5-turbo

    instances of special characters or symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.85
     citiz
    -0.80
     submar
    -0.76
    hement
    -0.76
     slashing
    -0.68
     Burgess
    -0.66
    orum
    -0.66
     volunte
    -0.66
     neighb
    -0.66
     ranc
    -0.65
    POSITIVE LOGITS
    CHAPTER
    0.98
    Beta
    0.95
    âĪ
    0.92
    Privacy
    0.91
    âĻ¥
    0.91
    Introduction
    0.91
    Author
    0.89
    Trivia
    0.88
    Version
    0.87
    MAL
    0.87
    Act Density 0.078%

    No Known Activations