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

    Neuronpedia

    INDEX
    Explanations

    foreign language text

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifying
    -0.70
     Sands
    -0.70
    WARD
    -0.68
     Dragonbound
    -0.67
     Perkins
    -0.66
    ified
    -0.66
    izable
    -0.65
     scrolling
    -0.64
     Mandela
    -0.64
     Jelly
    -0.64
    POSITIVE LOGITS
    ı
    1.44
    Ĵ
    1.40
    ĥ
    1.38
    ĸ
    1.38
    Ķ
    1.36
    İ
    1.35
    Ģ
    1.34
    Į
    1.33
    Ľ
    1.33
    ħ
    1.30
    Act Density 0.008%

    No Known Activations