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

    Neuronpedia

    INDEX
    Explanations

    numerical values or measurements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government oversight and regulatory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITNESS
    -0.45
    Anyway
    -0.44
    uphem
    -0.43
     alike
    -0.40
    depending
    -0.39
    ...?
    -0.39
    axter
    -0.38
    arthed
    -0.38
     suffice
    -0.37
    sama
    -0.37
    POSITIVE LOGITS
     and
    1.33
     &
    1.19
     AND
    0.98
    and
    0.91
    -,
    0.79
    &
    0.72
    ,
    0.70
    And
    0.69
     et
    0.69
     And
    0.65
    Act Density 2.817%

    No Known Activations