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

    Neuronpedia

    INDEX
    Explanations

    cryptic patterns that might include numbers, special characters, and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    key actions or concepts related to creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anski
    -0.93
     Ibrahim
    -0.84
     IM
    -0.82
    ZI
    -0.77
    iation
    -0.77
     Milan
    -0.77
     Rim
    -0.77
     Han
    -0.75
     Levin
    -0.75
    iban
    -0.74
    POSITIVE LOGITS
    Ĵ
    1.07
    UES
    0.94
    IJ
    0.87
    USA
    0.86
    ãĤ¯
    0.81
    ue
    0.80
    apesh
    0.79
    ules
    0.79
    ather
    0.79
    YS
    0.78
    Act Density 0.425%

    No Known Activations