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

    Neuronpedia

    INDEX
    Explanations

    timestamps or dates in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erea
    -0.17
    riad
    -0.15
    æĿī
    -0.15
    çłĤ
    -0.15
    owers
    -0.15
    mons
    -0.15
    ساÙĦ
    -0.14
     thi
    -0.14
    iasi
    -0.14
    rais
    -0.14
    POSITIVE LOGITS
    ços
    0.17
    ancel
    0.15
    bab
    0.15
    TECTED
    0.15
    abin
    0.15
    Gro
    0.13
    RY
    0.13
    DEFINED
    0.13
    acks
    0.13
    signed
    0.13
    Act Density 0.021%

    No Known Activations