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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _whitespace
    -0.17
     célib
    -0.16
     nouve
    -0.16
     seperate
    -0.16
    _utilities
    -0.15
     sout
    -0.14
    ÏĨη
    -0.14
    erras
    -0.14
     meille
    -0.14
     seper
    -0.14
    POSITIVE LOGITS
    nal
    0.33
    _infos
    0.25
    Infos
    0.25
    _nb
    0.23
    .nb
    0.22
    élé
    0.21
    Nb
    0.21
     :↵↵
    0.20
    _NB
    0.20
     «
    0.20
    Act Density 0.692%

    No Known Activations