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

    Neuronpedia

    INDEX
    Explanations

    phrases related to showcasing, demonstrating, or presenting characteristics or traits

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to exhibiting behaviors or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asha
    -0.69
     Debor
    -0.60
    soon
    -0.60
     Airlines
    -0.60
    lad
    -0.59
     distur
    -0.58
     unborn
    -0.58
    raft
    -0.57
     airliner
    -0.57
     Jah
    -0.57
    POSITIVE LOGITS
     considerable
    0.93
    stood
    0.85
     difficulty
    0.84
     degrees
    0.83
     distinct
    0.82
     similar
    0.82
     resemblance
    0.80
     similarities
    0.79
     strict
    0.79
     significant
    0.79
    Act Density 0.385%

    No Known Activations