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

    Neuronpedia

    INDEX
    Explanations

    characters from a non-English alphabet

    oai_token-act-pair · gpt-3.5-turbo

    unusual or non-standard characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sands
    -0.72
    WARD
    -0.71
     Perkins
    -0.71
    CLASSIFIED
    -0.69
     Carib
    -0.68
    izable
    -0.67
    stocks
    -0.67
     Mandela
    -0.66
    ified
    -0.65
     Dragonbound
    -0.65
    POSITIVE LOGITS
    ĥ
    1.53
    ķ
    1.45
    Ĵ
    1.45
    ī
    1.42
    İ
    1.42
    ħ
    1.42
    Ľ
    1.40
    Ģ
    1.40
    ĺ
    1.40
    ı
    1.39
    Act Density 0.016%

    No Known Activations