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

    Neuronpedia

    INDEX
    Explanations

    specific formatting and structural elements in academic or research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .fm
    -0.16
     Kin
    -0.14
     stagger
    -0.14
    ogenesis
    -0.14
     सà¤ķ
    -0.14
    ãĥªãĤ¹
    -0.13
    zent
    -0.13
    yal
    -0.13
    variants
    -0.13
    ç¡
    -0.13
    POSITIVE LOGITS
    ENSION
    0.15
     Witness
    0.14
    luv
    0.14
    vrier
    0.14
    odem
    0.14
    526
    0.14
     records
    0.14
    unset
    0.14
    .Enqueue
    0.13
    irket
    0.13
    Act Density 0.179%

    No Known Activations