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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies or research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MPU
    -0.16
    ondo
    -0.15
    rr
    -0.15
    orough
    -0.15
    Åijs
    -0.14
    CTOR
    -0.14
    ftware
    -0.14
    ikler
    -0.14
    midi
    -0.14
    VELO
    -0.13
    POSITIVE LOGITS
     ref
    0.20
    8
    0.17
    -generic
    0.15
    6
    0.15
    7
    0.14
    4
    0.14
    ovich
    0.14
    è¨
    0.14
    3
    0.14
    acier
    0.13
    Act Density 0.022%

    No Known Activations