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

    Neuronpedia

    INDEX
    Explanations

    code structures related to functions and their definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linger
    -0.15
     edits
    -0.15
    hl
    -0.15
     Boss
    -0.14
    xm
    -0.14
     Hutch
    -0.13
    ULLET
    -0.13
    ÑĩиÑĤ
    -0.13
    eryl
    -0.13
     Ary
    -0.13
    POSITIVE LOGITS
     #=>
    0.16
    ivalent
    0.15
    اخ
    0.15
    dol
    0.15
    itored
    0.14
    eler
    0.14
    ignon
    0.14
    zar
    0.14
    serter
    0.14
    воÑİ
    0.14
    Act Density 0.141%

    No Known Activations