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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal codes for colors followed by a symbol

    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
     contrace
    -0.84
    pmwiki
    -0.78
    milo
    -0.77
     mathemat
    -0.75
     recourse
    -0.68
     behav
    -0.67
    ategory
    -0.64
     compr
    -0.64
    isure
    -0.63
     territ
    -0.63
    POSITIVE LOGITS
    а
    1.07
    ·
    1.07
    в
    1.07
    ÏĤ
    1.01
    Ñĭ
    1.01
    м
    0.99
    ÙĦ
    0.95
    ׾
    0.94
    °
    0.94
    Ñĥ
    0.92
    Act Density 0.007%

    No Known Activations