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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or events related to competition or victory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ë¶Ħ
    -0.15
    .af
    -0.14
    anky
    -0.14
    annies
    -0.14
    opp
    -0.13
    vana
    -0.13
    aida
    -0.13
    _Mouse
    -0.13
    ANN
    -0.13
    QS
    -0.13
    POSITIVE LOGITS
    enco
    0.16
    brero
    0.15
    íĨ¤
    0.15
    enville
    0.15
    elman
    0.15
    chnitt
    0.15
    inclu
    0.14
    hibited
    0.14
    iyan
    0.14
    ying
    0.14
    Act Density 0.147%

    No Known Activations