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

    Neuronpedia

    INDEX
    Explanations

    words indicating singularity or specific items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.78
    المراجع
    -0.77
    Hentet
    -0.65
    مراجع
    -0.65
     uska
    -0.63
     ligiloj
    -0.62
     Theſe
    -0.62
     referenties
    -0.62
     móvel
    -0.61
     stumps
    -0.61
    POSITIVE LOGITS
     in
    0.75
     وفي
    0.73
    CloseOperation
    0.72
    InThe
    0.71
     Dalam
    0.69
    Nella
    0.67
    dalam
    0.66
     nella
    0.64
     In
    0.63
     dans
    0.63
    Act Density 0.498%

    No Known Activations