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

    Neuronpedia

    INDEX
    Explanations

    references to people and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entanto
    -1.06
    omiast
    -0.92
    however
    -0.83
     furthermore
    -0.82
     however
    -0.81
     moreover
    -0.81
    uttavia
    -0.80
     therefore
    -0.80
     obstante
    -0.79
    прочем
    -0.77
    POSITIVE LOGITS
    When
    1.02
     When
    0.97
     when
    0.84
    Every
    0.84
    During
    0.83
     During
    0.80
     Cuando
    0.79
    Sometimes
    0.77
     Every
    0.77
     WHEN
    0.77
    Act Density 0.475%

    No Known Activations