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

    Neuronpedia

    INDEX
    Explanations

    verbs that describe the action of using something

    oai_token-act-pair · gpt-3.5-turbo

    usages of the word "in" along with specific contexts or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abe
    -0.74
    rio
    -0.72
    osal
    -0.71
    ydia
    -0.71
    iable
    -0.70
    llah
    -0.70
    oulos
    -0.70
    ensable
    -0.69
    hedon
    -0.68
    76561
    -0.65
    POSITIVE LOGITS
     conjunction
    1.64
     lieu
    1.36
     tandem
    1.13
     moderation
    0.97
     vain
    0.97
     constructing
    0.95
     emergencies
    0.91
    ordinate
    0.90
     designing
    0.90
     combination
    0.89
    Act Density 0.190%

    No Known Activations