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

    Neuronpedia

    INDEX
    Explanations

    words related to technology, development, and software updates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    shown
    -0.70
    raid
    -0.66
    Discuss
    -0.65
    icons
    -0.65
    olor
    -0.65
    imon
    -0.64
    nor
    -0.64
    orst
    -0.64
    orthodox
    -0.63
    bons
    -0.62
    POSITIVE LOGITS
     undone
    1.12
     forth
    0.91
     roaring
    0.85
     crashing
    0.83
     flooding
    0.82
     ashore
    0.82
     pouring
    0.79
    leon
    0.75
     closer
    0.74
     out
    0.73
    Act Density 0.080%

    No Known Activations