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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to," particularly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inton
    -0.14
    enberg
    -0.14
    zw
    -0.14
    од
    -0.14
    upakan
    -0.14
    asio
    -0.13
    ům
    -0.13
    ücken
    -0.13
    hud
    -0.13
     Vegas
    -0.13
    POSITIVE LOGITS
    ãĤ¥
    0.16
    ë§Ŀ
    0.15
    eza
    0.14
    igans
    0.14
    _literals
    0.14
    LLL
    0.14
    μή
    0.14
    isode
    0.14
    /../
    0.13
    blick
    0.13
    Act Density 0.028%

    No Known Activations