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

    occurrences of the word "builds"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    error
    -0.67
     doubtful
    -0.63
    ajor
    -0.63
     fumble
    -0.61
     label
    -0.59
     reserve
    -0.58
    nown
    -0.57
     ALS
    -0.56
     slip
    -0.56
     caption
    -0.55
    POSITIVE LOGITS
     builds
    3.64
     installs
    1.75
     Build
    1.58
     build
    1.55
    Build
    1.51
    build
    1.47
     develops
    1.38
     mounts
    1.34
     mixes
    1.34
     setups
    1.32
    Act Density 0.020%

    No Known Activations