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

    Neuronpedia

    INDEX
    Explanations

    references to official documents and related dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chapters
    -0.15
     Chapters
    -0.15
     cand
    -0.15
    enal
    -0.14
    ;amp
    -0.14
     Chandler
    -0.14
    avia
    -0.14
    Ñıви
    -0.13
    ables
    -0.13
    ABCDE
    -0.13
    POSITIVE LOGITS
     dated
    0.27
    dated
    0.24
     issued
    0.20
    issued
    0.20
     letter
    0.18
    -signed
    0.18
     circular
    0.17
     signed
    0.16
     imz
    0.16
    ikel
    0.16
    Act Density 0.108%

    No Known Activations