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

    Neuronpedia

    INDEX
    Explanations

    instances of relational dependencies and interactions among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    harma
    -0.15
    pedia
    -0.15
    MITTED
    -0.14
    adla
    -0.13
    ample
    -0.13
    رÙĥ
    -0.13
    à¸ľà¸¥
    -0.13
    rupa
    -0.13
    ÏģÎŃ
    -0.13
    ublished
    -0.13
    POSITIVE LOGITS
    eros
    0.16
    ivan
    0.15
    aku
    0.15
     Scar
    0.15
    ukan
    0.15
    ordin
    0.15
    375
    0.14
    uco
    0.14
    uko
    0.14
    660
    0.14
    Act Density 0.104%

    No Known Activations