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

    Neuronpedia

    INDEX
    Explanations

    specific technology-related terms and names

    oai_token-act-pair · gpt-3.5-turbo

    the word "by" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ì
    -0.81
    uality
    -0.79
    heimer
    -0.73
    stakes
    -0.72
    ãĥ´ãĤ¡
    -0.71
    ashtra
    -0.68
    ovy
    -0.67
    ãĤ¦ãĤ¹
    -0.66
    Ó
    -0.66
    Ñĭ
    -0.66
    POSITIVE LOGITS
     virtue
    1.06
    products
    0.98
     contractors
    0.90
     employers
    0.87
     clients
    0.86
     locals
    0.85
     collectors
    0.84
     entities
    0.84
     vendors
    0.84
     passers
    0.83
    Act Density 0.156%

    No Known Activations