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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms indicating strict rules or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orra
    -0.20
    .scalablytyped
    -0.16
    atik
    -0.16
    rych
    -0.15
    agma
    -0.15
    zdy
    -0.15
    orget
    -0.14
     ?>&
    -0.14
    strap
    -0.14
    è®
    -0.14
    POSITIVE LOGITS
    ly
    0.16
    ħį
    0.15
    ried
    0.15
    баÑĩ
    0.14
     Han
    0.14
    inda
    0.14
    yon
    0.14
    roat
    0.14
    rou
    0.14
    rie
    0.14
    Act Density 0.003%

    No Known Activations