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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "copy" and its variations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    if
    -0.17
    iras
    -0.17
    rd
    -0.16
    ired
    -0.16
    ly
    -0.15
    ishi
    -0.14
    наÑĢ
    -0.14
    lest
    -0.14
    st
    -0.14
    re
    -0.13
    POSITIVE LOGITS
    .deepcopy
    0.23
    /cop
    0.19
    aset
    0.18
    ieux
    0.16
    práv
    0.16
    irket
    0.16
    až
    0.15
     lẽ
    0.14
    živ
    0.14
    riot
    0.14
    Act Density 0.032%

    No Known Activations