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

    Neuronpedia

    INDEX
    Explanations

    uses of code and code-like syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sei
    -0.17
    hdl
    -0.16
     gr
    -0.16
    aises
    -0.14
     Princip
    -0.14
    ноÑĩ
    -0.14
    aight
    -0.14
    isay
    -0.13
    STALL
    -0.13
     bol
    -0.13
    POSITIVE LOGITS
    ude
    0.16
     Indexed
    0.14
    lix
    0.14
    ao
    0.14
    nev
    0.14
    .ru
    0.14
    addin
    0.13
    liÄį
    0.13
    iline
    0.13
    boy
    0.13
    Act Density 0.005%

    No Known Activations