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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to authority figures or systems of governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rock
    -0.55
     Negro
    -0.54
     Mug
    -0.53
    Drug
    -0.53
    ¥ŀ
    -0.53
    PN
    -0.53
    Anth
    -0.53
    zac
    -0.52
    senal
    -0.51
     kingdom
    -0.51
    POSITIVE LOGITS
    and
    0.83
    &
    0.78
     AND
    0.76
    âķIJ
    0.73
     &
    0.70
    erves
    0.70
     ±
    0.66
    ilaterally
    0.65
     and
    0.65
    ortium
    0.64
    Act Density 0.579%

    No Known Activations