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

    Neuronpedia

    INDEX
    Explanations

    words related to invention and innovation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to invention and innovative concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    accompan
    -0.81
     challeng
    -0.72
    head
    -0.66
     cumbers
    -0.66
    HEAD
    -0.64
    ISON
    -0.64
     proximity
    -0.63
    CHR
    -0.63
     metab
    -0.59
     inquiries
    -0.59
    POSITIVE LOGITS
    eers
    1.08
    eenth
    1.03
    ricular
    1.00
    eer
    0.99
    een
    0.97
    urous
    0.95
    ron
    0.94
    vent
    0.93
    actory
    0.92
    ories
    0.91
    Act Density 0.011%

    No Known Activations