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

    Neuronpedia

    INDEX
    Explanations

    numerical representations, particularly related to counting or ordering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cumhur
    -0.19
     Ch
    -0.16
    Äįen
    -0.16
    Äįin
    -0.16
    instein
    -0.15
    fty
    -0.15
    ãĥ¼ãĥĸ
    -0.15
    Https
    -0.14
    ãĥ¼ãĥŀ
    -0.14
    lit
    -0.13
    POSITIVE LOGITS
     Ep
    0.29
     ep
    0.28
    Ep
    0.23
     Ñįп
    0.17
    _ep
    0.17
    ep
    0.17
     bonus
    0.16
     Author
    0.16
     Ack
    0.16
    ,ep
    0.16
    Act Density 0.004%

    No Known Activations