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

    Neuronpedia

    INDEX
    Explanations

    scientific or technical processes involving various subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to "processes" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     earnest
    -0.68
    noon
    -0.67
     cheap
    -0.67
     Parables
    -0.65
     brothers
    -0.64
    gged
    -0.64
     humble
    -0.63
    rel
    -0.62
    ged
    -0.61
    rav
    -0.61
    POSITIVE LOGITS
     processes
    1.36
     process
    0.91
     Process
    0.90
    process
    0.88
    afety
    0.87
    hops
    0.85
    ctl
    0.81
     Ceres
    0.80
    Ó
    0.78
    ional
    0.76
    Act Density 0.013%

    No Known Activations