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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" indicating existence or identity

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.77
    fortunately
    -0.71
    terday
    -0.71
    rones
    -0.70
    't
    -0.67
    eday
    -0.66
    ãĥ¼ãĥ«
    -0.66
    then
    -0.65
     doubtless
    -0.65
     surely
    -0.63
    POSITIVE LOGITS
     metic
    0.79
     fertile
    0.66
     influenced
    0.66
     swayed
    0.62
     progressing
    0.62
     quite
    0.62
     able
    0.61
     synonymous
    0.61
     involved
    0.60
    que
    0.60
    Act Density 0.130%

    No Known Activations