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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating viewpoints or perspectives

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    saraba
    -0.63
     Flag
    -0.56
    Flag
    -0.52
    THISDAY
    -0.50
    Jereo
    -0.50
     nóng
    -0.50
     khỏi
    -0.50
    Rujukan
    -0.49
     emploi
    -0.48
    pherals
    -0.47
    POSITIVE LOGITS
     myſelf
    0.69
     viewpoint
    0.66
     صوتيه
    0.66
     standpoint
    0.66
     houſe
    0.63
     Majefty
    0.63
     ſever
    0.61
     للاسماء
    0.61
     crdi
    0.61
     juſ
    0.60
    Act Density 0.013%

    No Known Activations