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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "of" followed by various contextually relevant terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agre
    -0.72
     fert
    -0.70
    ahime
    -0.68
    fore
    -0.65
    omo
    -0.64
     condem
    -0.63
     arrang
    -0.62
     grooming
    -0.61
     surpr
    -0.60
     streng
    -0.59
    POSITIVE LOGITS
    teen
    0.75
    icial
    0.74
     dozen
    0.72
    ources
    0.69
    teenth
    0.66
    uits
    0.66
    course
    0.62
     Cups
    0.62
    ife
    0.61
    clusions
    0.60
    Act Density 0.069%

    No Known Activations