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

    Neuronpedia

    INDEX
    Explanations

    names of researchers and their contributions to scientific fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [section
    -0.17
    rende
    -0.16
    aston
    -0.16
    ovy
    -0.16
    ienia
    -0.16
    stations
    -0.15
     пÑĢид
    -0.14
    εÏģγ
    -0.14
    обÑĢаÐ
    -0.14
    anmar
    -0.14
    POSITIVE LOGITS
    uki
    0.15
    thed
    0.14
     macro
    0.14
    Macro
    0.14
     his
    0.14
    OfString
    0.14
     false
    0.13
     if
    0.13
     Abs
    0.13
    esi
    0.13
    Act Density 0.099%

    No Known Activations