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

    Neuronpedia

    INDEX
    Explanations

    patterns of underscores or special characters followed by numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    //
    -0.57
     Athenians
    -0.53
     nymphs
    -0.53
     comigo
    -0.52
     Netanyahu
    -0.52
     sandstones
    -0.52
     correto
    -0.50
     //
    -0.49
     legais
    -0.49
     didst
    -0.49
    POSITIVE LOGITS
    ')['
    0.76
     مُعرِّف
    0.72
    multirow
    0.72
    پیوند
    0.71
     виправивши
    0.71
     /\.
    0.71
    ughty
    0.70
    Gön
    0.69
     esternos
    0.69
    ropriate
    0.67
    Act Density 0.149%

    No Known Activations