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

    Neuronpedia

    INDEX
    Explanations

    words associated with addition, increasing, or enhancing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "add" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.71
    ãĥīãĥ©ãĤ´ãĥ³
    -0.64
    ··
    -0.63
    soType
    -0.63
    COLOR
    -0.63
    Consumer
    -0.62
    é¾
    -0.61
    âĸ¬
    -0.61
     HRC
    -0.60
     departure
    -0.60
    POSITIVE LOGITS
    itional
    1.22
    itionally
    1.16
    icted
    1.15
    ened
    1.05
    ictive
    1.03
    resses
    1.03
    ressed
    1.02
    ening
    1.01
    iction
    1.00
    ressing
    0.99
    Act Density 0.017%

    No Known Activations