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

    Neuronpedia

    INDEX
    Explanations

    coding elements related to input handling and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -fw
    -0.16
    /is
    -0.15
    ats
    -0.15
    ppard
    -0.15
    eton
    -0.14
    eno
    -0.14
    itto
    -0.14
    ä¹Ĺ
    -0.14
     même
    -0.14
    /not
    -0.14
    POSITIVE LOGITS
    /output
    0.26
    ters
    0.24
    ted
    0.23
    ting
    0.21
    -output
    0.21
    MethodManager
    0.16
    tings
    0.16
    TING
    0.15
    elman
    0.15
    nist
    0.15
    Act Density 0.031%

    No Known Activations