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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sections or paragraphs in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endnu
    -0.76
     løpet
    -0.75
     møte
    -0.75
     måte
    -0.74
     vapors
    -0.73
    ագրություններ
    -0.73
     sjø
    -0.72
     eksemp
    -0.71
     stedet
    -0.71
     ſch
    -0.71
    POSITIVE LOGITS
    kegaard
    0.59
    abestanden
    0.56
     Blom
    0.56
    gitte
    0.55
    gaard
    0.52
    Lise
    0.52
     Linde
    0.52
     Madsen
    0.52
    Jensen
    0.51
    Sve
    0.50
    Act Density 0.229%

    No Known Activations