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

    Neuronpedia

    INDEX
    Explanations

    phrases related to explaining or discussing different perspectives or ideas

    oai_token-act-pair · gpt-3.5-turbo

    prepositions used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #$
    -0.79
    Champ
    -0.67
     lasted
    -0.66
    CLASSIFIED
    -0.65
    $
    -0.63
    wat
    -0.61
    ENCE
    -0.61
    llor
    -0.61
    rolet
    -0.60
     Illustrated
    -0.60
    POSITIVE LOGITS
     lieu
    1.38
     accordance
    1.25
     order
    1.19
     favor
    1.18
    effic
    1.17
    ordinate
    1.13
     vitro
    1.08
    humane
    1.08
     spite
    1.06
     situ
    1.05
    Act Density 0.398%

    No Known Activations