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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to news events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geist
    -0.88
    adeon
    -0.69
    lins
    -0.68
    hower
    -0.66
    galitarian
    -0.64
    ageddon
    -0.64
    won
    -0.63
    akeru
    -0.61
     âĢķ
    -0.61
    omics
    -0.60
    POSITIVE LOGITS
     longest
    1.22
     culmination
    1.14
     equivalent
    1.10
     latter
    1.08
     holiest
    1.08
     largest
    1.06
     deadliest
    1.01
     highest
    1.00
     busiest
    0.97
     oldest
    0.97
    Act Density 0.142%

    No Known Activations