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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and notable figures in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¢ħ
    -0.14
    .blogspot
    -0.13
    ãĥ¼ãĥ
    -0.13
    jang
    -0.12
     teng
    -0.12
    .isNullOrEmpty
    -0.12
    бÑĥÑĢг
    -0.12
    èĽĩ
    -0.12
     Seymour
    -0.12
    лÑİ
    -0.11
    POSITIVE LOGITS
    _w
    0.27
    *w
    0.27
    -w
    0.27
    .w
    0.25
    w
    0.25
    	W
    0.24
    .W
    0.24
    _W
    0.24
     ãĤ¦
    0.24
     W
    0.24
    Act Density 0.473%

    No Known Activations