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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to physical attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to temperature variations and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilitary
    -0.65
    ptin
    -0.65
     coli
    -0.62
    ounter
    -0.61
     Regulatory
    -0.59
    ppa
    -0.59
    GAME
    -0.59
     Agric
    -0.59
     subscribing
    -0.58
     irrig
    -0.58
    POSITIVE LOGITS
    ness
    1.91
    nesses
    1.62
    NESS
    1.41
    liness
    1.02
    ity
    0.96
     ones
    0.93
    cies
    0.92
    eness
    0.91
    ened
    0.90
    itude
    0.90
    Act Density 0.357%

    No Known Activations