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

    Neuronpedia

    INDEX
    Explanations

    elements related to distinctions and comparisons in processes or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyu
    -0.15
    yp
    -0.15
     '{$
    -0.14
    ãĥ³ãĥĸ
    -0.14
    rag
    -0.14
    à¸Īà¸Ļ
    -0.13
    aya
    -0.13
    RTL
    -0.13
    ada
    -0.13
     Schul
    -0.13
    POSITIVE LOGITS
     discussed
    0.40
     below
    0.32
     discuss
    0.31
     see
    0.31
     later
    0.29
    disc
    0.29
     discussion
    0.28
     See
    0.28
     discusses
    0.27
    below
    0.27
    Act Density 0.320%

    No Known Activations