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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "including"

    oai_token-act-pair · gpt-3.5-turbo

    the word "including" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iny
    -0.78
    rait
    -0.78
    iri
    -0.76
    athy
    -0.76
    iet
    -0.73
    uters
    -0.73
    ules
    -0.71
    ould
    -0.71
    ael
    -0.71
    ochond
    -0.71
    POSITIVE LOGITS
     those
    0.74
     yours
    0.67
     ours
    0.65
     ones
    0.64
     possibly
    0.62
     Daredevil
    0.62
    worth
    0.61
    ãĥĸ
    0.61
     references
    0.60
     Blaster
    0.60
    Act Density 0.065%

    No Known Activations