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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing precision and specificity in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    าะ
    -0.17
    udeau
    -0.16
    sg
    -0.16
    ivec
    -0.16
    [section
    -0.15
    angered
    -0.15
    StackSize
    -0.14
    Č↵
    -0.14
    essian
    -0.14
    phinx
    -0.14
    POSITIVE LOGITS
     Overnight
    0.15
     Friedman
    0.14
    itin
    0.14
    otas
    0.14
     Polo
    0.14
    ody
    0.14
    zin
    0.14
    á»ĭnh
    0.14
     Stable
    0.14
    lotte
    0.14
    Act Density 0.033%

    No Known Activations