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

    Neuronpedia

    INDEX
    Explanations

    expressions of absurdity or humor related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anie
    -0.19
    istrovstvÃŃ
    -0.17
    elter
    -0.16
    iek
    -0.16
    odes
    -0.15
    anes
    -0.15
    iyon
    -0.14
    zym
    -0.14
    root
    -0.14
    aver
    -0.14
    POSITIVE LOGITS
    ostel
    0.17
    -looking
    0.16
    lsen
    0.16
    Ù
    0.15
    ingly
    0.15
     Clarkson
    0.15
    ochen
    0.14
    rouw
    0.14
    eme
    0.14
    mente
    0.14
    Act Density 0.005%

    No Known Activations