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

    Neuronpedia

    INDEX
    Explanations

    formatted numerical information, particularly time and date representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.45
     Haupts
    -0.44
    érience
    -0.41
     Reihenfolge
    -0.40
     keamanan
    -0.40
     keber
    -0.39
     rumahnya
    -0.39
     kuiten
    -0.39
     amarillas
    -0.38
    ękuję
    -0.38
    POSITIVE LOGITS
     lccn
    0.60
    時
    0.50
     <<<<<<<<<<<<<<
    0.47
    IntoConstraints
    0.46
     ffilmiau
    0.46
     uhr
    0.46
    时
    0.43
    ArrowToggle
    0.42
    chede
    0.40
    ⁡
    0.40
    Act Density 0.164%

    No Known Activations