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

    Neuronpedia

    INDEX
    Explanations

    phrases related to obtaining additional information or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by requests for more information/details

    np_acts-logits-general · gemini-2.0-flash

    for more information/details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <=",
    -0.64
     يتيمه
    -0.63
     فريبيس
    -0.60
     resourceCulture
    -0.57
    RegressionTest
    -0.57
    -0.56
    Portail
    -0.56
    OGND
    -0.54
     '\\;'
    -0.52
    JspWriter
    -0.50
    POSITIVE LOGITS
     more
    1.68
     details
    1.38
     further
    1.27
    more
    1.21
     More
    1.15
     mehr
    1.12
    details
    1.10
    further
    1.08
     więcej
    1.07
     information
    1.06
    Act Density 0.205%

    No Known Activations