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

    Neuronpedia

    INDEX
    Explanations

    Russian text containing special characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xus
    -0.88
     deaf
    -0.84
     Hole
    -0.72
    warm
    -0.68
    fruit
    -0.68
     Sapphire
    -0.66
     tremend
    -0.65
    kefeller
    -0.64
     satell
    -0.64
    enei
    -0.64
    POSITIVE LOGITS
    enance
    1.04
    ÑĢ
    1.02
    оÐ
    1.00
    Ñĥ
    0.92
    о
    0.86
    а
    0.85
    л
    0.85
    riad
    0.84
    tal
    0.80
    rito
    0.80
    Act Density 0.019%

    No Known Activations