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

    Neuronpedia

    INDEX
    Explanations

    words related to construction or building

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "build" and its variations indicating construction or creation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acting
    -0.69
    soDeliveryDate
    -0.68
    nown
    -0.68
    lah
    -0.66
    ajor
    -0.65
    joy
    -0.64
    icent
    -0.64
     SOS
    -0.64
     MIA
    -0.64
     Humane
    -0.63
    POSITIVE LOGITS
     build
    3.44
     builds
    2.49
     Build
    2.41
    Build
    2.26
    build
    2.21
     rebuild
    1.89
     built
    1.78
     buildup
    1.75
     building
    1.63
    Building
    1.55
    Act Density 0.026%

    No Known Activations