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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals or names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and terms associated with individuals or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤª
    -0.81
    æµ
    -0.80
    ãĤ¶
    -0.74
    Privacy
    -0.72
    DEV
    -0.72
    ãĤ¹ãĥĪ
    -0.69
    Benz
    -0.69
     Instruments
    -0.68
     Seal
    -0.67
     Cities
    -0.65
    POSITIVE LOGITS
    ews
    0.85
    lines
    0.81
    aturally
    0.77
    orter
    0.77
    uala
    0.73
     likeness
    0.73
    otle
    0.73
    Lago
    0.72
    leted
    0.72
     graded
    0.71
    Act Density 0.020%

    No Known Activations