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

    Neuronpedia

    INDEX
    Explanations

    references to specific publishers or publishing entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aten
    -0.16
    ught
    -0.15
    harma
    -0.15
    imension
    -0.15
    lane
    -0.14
    ÄĽt
    -0.14
    urse
    -0.14
     Sas
    -0.14
    ĥ
    -0.14
    \Lib
    -0.14
    POSITIVE LOGITS
     Simon
    0.21
     sim
    0.20
     Gar
    0.18
    Simon
    0.18
    amus
    0.17
    _SIM
    0.17
    otas
    0.16
     GAR
    0.16
    chester
    0.16
    (sim
    0.16
    Act Density 0.008%

    No Known Activations