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

    Neuronpedia

    INDEX
    Explanations

    string patterns and punctuation marks that indicate quotes or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stället
    -0.61
    <>();
    -0.59
     kapcsolat
    -0.58
    sprzedam
    -0.57
    namely
    -0.57
    couvrez
    -0.56
    lámpara
    -0.56
     nemlig
    -0.55
     arbete
    -0.55
    chaqueta
    -0.55
    POSITIVE LOGITS
     normal
    0.73
    Autoritní
    0.72
     ‘
    0.72
     “
    0.65
    normal
    0.64
    :✨
    0.62
    afficheront
    0.60
     real
    0.60
    zinger
    0.57
    ifs
    0.57
    Act Density 0.161%

    No Known Activations