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

    Neuronpedia

    INDEX
    Explanations

    numerical references and counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thousands
    -0.18
     BOTH
    -0.17
     both
    -0.17
     Numerous
    -0.17
     thousands
    -0.16
    åIJĦç§į
    -0.16
     Various
    -0.15
    amen
    -0.15
    許
    -0.15
    éĤ£äºĽ
    -0.15
    POSITIVE LOGITS
     different
    0.32
     dozen
    0.29
     separate
    0.28
     sets
    0.28
    /all
    0.26
    different
    0.26
    -thirds
    0.25
    teenth
    0.25
     of
    0.25
     seperate
    0.25
    Act Density 0.294%

    No Known Activations