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

    Neuronpedia

    INDEX
    Explanations

    people's names often preceded by their titles or aliases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating additional information about a subject or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maxwell
    -0.67
    orest
    -0.61
    anwhile
    -0.60
    rison
    -0.60
    folios
    -0.60
    é¾įå¥ij士
    -0.60
     Banner
    -0.58
    omore
    -0.58
    adena
    -0.58
    ¶ħ
    -0.58
    POSITIVE LOGITS
     happens
    0.92
     known
    0.82
     referred
    0.81
     serves
    0.79
     served
    0.78
     applies
    0.77
    NESS
    0.77
     qualifies
    0.75
     includes
    0.73
     exists
    0.70
    Act Density 0.102%

    No Known Activations