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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical characteristics and attributes

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to size, simplicity, and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appiness
    -0.66
    plet
    -0.65
    sis
    -0.64
    hower
    -0.63
    doms
    -0.62
    gemony
    -0.62
    orns
    -0.60
    livion
    -0.60
    anton
    -0.59
    zinski
    -0.58
    POSITIVE LOGITS
     enough
    1.46
    enough
    1.04
     compared
    0.99
     insofar
    0.92
     and
    0.89
     nonetheless
    0.88
     Enough
    0.87
     but
    0.85
     owing
    0.83
     yet
    0.83
    Act Density 0.287%

    No Known Activations