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

    Neuronpedia

    INDEX
    Explanations

    the verb "to be" in different forms and tenses

    oai_token-act-pair · gpt-3.5-turbo

    the use of the verb "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.72
    ertodd
    -0.68
    oire
    -0.67
    aire
    -0.65
    ileaks
    -0.65
    lished
    -0.65
    osate
    -0.64
    ry
    -0.64
    alus
    -0.64
     Gren
    -0.61
    POSITIVE LOGITS
     selves
    0.90
     themselves
    0.78
    wolf
    0.77
    selves
    0.75
    MpServer
    0.70
    models
    0.68
     successors
    0.66
    wolves
    0.66
     not
    0.66
    atically
    0.66
    Act Density 0.316%

    No Known Activations