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

    Neuronpedia

    INDEX
    Explanations

    triggers related to exclamations and emotional expressions

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters or sequences that indicate a formatting or encoding issue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shant
    -0.70
     Tid
    -0.70
     photoc
    -0.69
     mete
    -0.67
     Shap
    -0.65
     seiz
    -0.64
     Xan
    -0.64
     horizont
    -0.63
     Synd
    -0.63
     Drawn
    -0.61
    POSITIVE LOGITS
    ķ
    1.15
    «
    1.11
    Ŀ
    1.06
    Ĵ
    1.04
    Ń
    1.04
    ĸ
    1.03
    ¬
    1.03
    ´
    1.03
    ĵ
    1.02
    ª
    1.02
    Act Density 0.118%

    No Known Activations