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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe or compare something to a specific example

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĭĴ
    -0.17
    opoulos
    -0.16
    urai
    -0.16
    chet
    -0.16
     Arth
    -0.16
    ccione
    -0.14
    rů
    -0.14
    æ´ª
    -0.14
     Rossi
    -0.14
    еÑĪ
    -0.13
    POSITIVE LOGITS
     tol
    0.17
     Mug
    0.16
     Wass
    0.15
    ulp
    0.15
    :↵
    0.14
     Digit
    0.14
     '((
    0.14
    :↵↵↵↵
    0.14
    -command
    0.13
    Digit
    0.13
    Act Density 0.080%

    No Known Activations