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

    Neuronpedia

    INDEX
    Explanations

    statements indicating the absence of proof or indication of a particular claim

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the presence or absence of evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eals
    -0.74
    quer
    -0.72
    eteria
    -0.72
    inis
    -0.71
    xtap
    -0.70
    appropriately
    -0.69
    aughs
    -0.68
    semble
    -0.66
    iery
    -0.66
    inion
    -0.65
    POSITIVE LOGITS
     whatsoever
    1.03
     indicating
    1.01
     suggesting
    0.97
     linking
    0.97
     that
    0.89
     of
    0.74
     contradict
    0.74
     suggestive
    0.73
     tying
    0.73
     suggest
    0.71
    Act Density 0.069%

    No Known Activations