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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a promise or commitment

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -1.06
     Theſe
    -0.95
     myſelf
    -0.94
     ſeveral
    -0.94
     itſelf
    -0.92
     ſhall
    -0.88
     Мексичка
    -0.88
     Houſe
    -0.88
     fhall
    -0.87
     Majefty
    -0.87
    POSITIVE LOGITS
     trekken
    0.59
     For
    0.59
     plastiques
    0.56
     By
    0.56
     fram
    0.55
     Porque
    0.55
    raltar
    0.54
    For
    0.52
     since
    0.51
     perchè
    0.51
    Act Density 0.023%

    No Known Activations