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

    Neuronpedia

    INDEX
    Explanations

    words with a mix of letters, numbers, and special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Forth
    -0.83
    ashtra
    -0.81
    aday
    -0.77
     Constantine
    -0.71
     Finch
    -0.69
    itaire
    -0.69
    20439
    -0.68
     Bethlehem
    -0.67
     Thumbnails
    -0.65
     Rossi
    -0.64
    POSITIVE LOGITS
    §
    1.29
    Ĥ¬
    1.25
    ĭ
    1.24
    Ĥ
    1.15
    ¹
    1.13
    ²
    1.12
    ĺ
    1.12
     ë
    1.11
    Ħ
    1.10
    ¬¼
    1.10
    Act Density 0.010%

    No Known Activations