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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "acknowledgment" or similar terms related to recognition or acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hlav
    -0.17
    912
    -0.14
     Gry
    -0.14
    ẽ
    -0.14
    веÑĤ
    -0.14
    232
    -0.13
     Dude
    -0.13
    arching
    -0.13
     spiral
    -0.13
    ève
    -0.13
    POSITIVE LOGITS
    амп
    0.15
    eldon
    0.14
    ĤŃ
    0.14
    ìĸij
    0.14
    QUI
    0.14
     harmless
    0.14
    lectic
    0.13
    umont
    0.13
     semp
    0.13
    uffman
    0.13
    Act Density 0.006%

    No Known Activations