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

    Neuronpedia

    INDEX
    Explanations

    legal or legislative terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant statistical or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angu
    -0.77
    laughter
    -0.71
    ikawa
    -0.71
    untarily
    -0.70
    endo
    -0.66
    tsy
    -0.65
    sburg
    -0.64
    ved
    -0.63
    ãĤ¢ãĥ«
    -0.61
    vale
    -0.61
    POSITIVE LOGITS
     however
    1.22
     meanwhile
    1.14
     moreover
    1.09
     consisting
    0.97
     comprising
    0.96
     alas
    0.93
     dubbed
    0.92
     nicknamed
    0.91
     coupled
    0.91
     which
    0.90
    Act Density 0.155%

    No Known Activations