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

    Neuronpedia

    INDEX
    Explanations

    instances of hexadecimal numbers or specific code-related tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifique
    -0.17
    fak
    -0.16
    ÑĢеж
    -0.15
    iaux
    -0.15
    fgang
    -0.14
    loor
    -0.14
    ivalence
    -0.14
    iface
    -0.14
    formance
    -0.14
    endar
    -0.14
    POSITIVE LOGITS
    jem
    0.15
    ustr
    0.14
    zilla
    0.14
    /src
    0.14
     Kingdom
    0.14
    bug
    0.14
    åIJ¹
    0.14
     civilian
    0.14
     DISP
    0.14
     Kush
    0.13
    Act Density 0.001%

    No Known Activations