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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters and studies/research findings

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angu
    -0.72
    untarily
    -0.67
    laughter
    -0.67
    tsy
    -0.66
    ikawa
    -0.63
    animate
    -0.63
    antis
    -0.62
    sburg
    -0.62
    lly
    -0.62
    "},"
    -0.61
    POSITIVE LOGITS
     however
    1.32
     which
    1.16
     meanwhile
    1.15
     dubbed
    1.13
     titled
    1.07
     moreover
    1.03
     consisting
    1.01
     entitled
    0.97
     comprising
    0.97
     nicknamed
    0.97
    Act Density 0.145%

    No Known Activations