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

    Neuronpedia

    INDEX
    Explanations

    references to product recalls or withdrawals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    иÑģÑģ
    -0.15
    uzzi
    -0.15
    odox
    -0.15
    untu
    -0.14
     sond
    -0.14
    -budget
    -0.14
    ç°
    -0.14
    ersh
    -0.14
     Classified
    -0.14
     kå
    -0.13
    POSITIVE LOGITS
     label
    0.35
     labels
    0.30
     labeling
    0.29
     packaging
    0.28
     ingredient
    0.25
    label
    0.25
     manufacturer
    0.24
     Label
    0.24
    -label
    0.23
    Label
    0.23
    Act Density 0.109%

    No Known Activations