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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" followed by various contexts and modalities

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oras
    -0.71
    berus
    -0.64
     Tale
    -0.63
     Dynamics
    -0.63
     relativity
    -0.61
     dynamics
    -0.61
    anos
    -0.61
     corpus
    -0.60
     Manufact
    -0.60
     Inher
    -0.60
    POSITIVE LOGITS
     glad
    1.09
     thankful
    1.00
     grateful
    0.99
     able
    0.99
     delighted
    0.94
     honest
    0.94
     amazed
    0.93
     damned
    0.93
     thrilled
    0.93
     blogging
    0.91
    Act Density 0.097%

    No Known Activations