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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific code syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chré
    -0.84
     دیکھیے
    -0.84
     avoient
    -0.73
    Jeografia
    -0.73
     šķ
    -0.72
     alfo
    -0.71
     Comprometido
    -0.71
    subsubsection
    -0.69
     Monfieur
    -0.69
     ProtoMessage
    -0.69
    POSITIVE LOGITS
    BagConstraints
    0.91
     Wied
    0.67
    CONSIN
    0.60
     Stur
    0.60
     Sko
    0.59
     Mal
    0.59
     Wid
    0.56
    mallows
    0.56
    물
    0.54
     str
    0.54
    Act Density 0.025%

    No Known Activations