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

    Neuronpedia

    INDEX
    Explanations

    references to specific subjects and their roles in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -flat
    -0.15
    aic
    -0.14
    lassian
    -0.14
     Geoff
    -0.14
     flat
    -0.14
     en
    -0.14
     Mash
    -0.14
    ä¸ĺ
    -0.14
    Äįet
    -0.14
    draul
    -0.14
    POSITIVE LOGITS
     basis
    0.20
     upon
    0.20
    upon
    0.19
     Basis
    0.17
    basis
    0.17
    onto
    0.17
     Upon
    0.17
     تÙħر
    0.16
    Upon
    0.16
    Æ¡n
    0.15
    Act Density 0.029%

    No Known Activations