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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "input" and its various contexts in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¹Ĺ
    -0.18
    -fw
    -0.15
    acey
    -0.15
    auge
    -0.15
    infeld
    -0.15
    eno
    -0.14
    ito
    -0.14
    iana
    -0.14
     OF
    -0.14
     même
    -0.14
    POSITIVE LOGITS
    ters
    0.25
    /output
    0.23
    ted
    0.22
    ting
    0.20
    -output
    0.18
    386
    0.17
    TING
    0.16
    MethodManager
    0.16
    tings
    0.15
    MMdd
    0.15
    Act Density 0.031%

    No Known Activations