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

    Neuronpedia

    INDEX
    Explanations

    technical information related to products or devices

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Events
    -0.75
    pedia
    -0.73
     Isles
    -0.73
    gom
    -0.71
    usercontent
    -0.71
     Deaths
    -0.71
    politics
    -0.70
    bart
    -0.68
    ossom
    -0.68
     Blaz
    -0.67
    POSITIVE LOGITS
     equipped
    1.39
     fitted
    1.31
     priced
    1.29
     designed
    1.26
     rated
    1.26
     coated
    1.23
     marketed
    1.21
     manufactured
    1.21
     adorned
    1.19
     housed
    1.18
    Act Density 0.192%

    No Known Activations