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

    Neuronpedia

    INDEX
    Explanations

    pairs of verbs and their corresponding direct objects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "oversee" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Secondly
    -0.73
    govtrack
    -0.72
     secondly
    -0.68
    olid
    -0.67
     suscept
    -0.65
    False
    -0.63
    mpeg
    -0.62
    ening
    -0.62
    iddler
    -0.61
    osponsors
    -0.61
    POSITIVE LOGITS
     overseeing
    1.17
     oversee
    0.85
    orship
    0.85
    stration
    0.85
     oversaw
    0.84
     overseen
    0.84
    İĭ
    0.77
     delegated
    0.74
     oversees
    0.70
    ership
    0.69
    Act Density 0.052%

    No Known Activations