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

    Neuronpedia

    INDEX
    Explanations

    words related to exaggeration, simplification, or excessiveness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to over- and under-representation or issues of excess in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Albion
    -0.76
     Gemini
    -0.68
     Coffin
    -0.66
     Romans
    -0.66
    Reviewed
    -0.66
     Panther
    -0.65
     Bullets
    -0.65
    uyomi
    -0.65
    DragonMagazine
    -0.63
     Franch
    -0.62
    POSITIVE LOGITS
    aturated
    1.19
    ourced
    1.18
    impl
    1.05
    ights
    1.04
    igned
    1.00
    aturation
    0.97
    ources
    0.97
    olicited
    0.96
    oles
    0.95
    ocial
    0.95
    Act Density 0.029%

    No Known Activations