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

    Neuronpedia

    INDEX
    Explanations

    punctuation and indicators of conclusions or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (Of
    -0.17
     ero
    -0.16
    shake
    -0.15
    erra
    -0.14
     er
    -0.14
    stant
    -0.13
    ãĤ¢ãĥ¼
    -0.13
    velop
    -0.13
    etype
    -0.13
    kc
    -0.13
    POSITIVE LOGITS
    eldorf
    0.19
    .abstract
    0.19
    uder
    0.18
    osg
    0.16
    agher
    0.15
    alach
    0.15
    olk
    0.15
    UNCT
    0.14
    olv
    0.14
    à¹Īาà¸ĩ
    0.14
    Act Density 0.007%

    No Known Activations