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

    Neuronpedia

    INDEX
    Explanations

    instances of actions taken by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "took" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agre
    -0.71
    earances
    -0.67
     david
    -0.65
    eers
    -0.64
    Cong
    -0.63
     sidebar
    -0.62
     Smile
    -0.62
    ler
    -0.62
     density
    -0.61
     [+]
    -0.59
    POSITIVE LOGITS
    aways
    1.08
     advantage
    1.03
     aback
    0.96
     heed
    0.91
     refuge
    0.86
     care
    0.85
    arnaev
    0.85
    autions
    0.84
     pains
    0.84
     precedence
    0.82
    Act Density 0.106%

    No Known Activations