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

    Neuronpedia

    INDEX
    Explanations

    uncertainties and questions regarding relationships and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OOK
    -0.15
     raw
    -0.15
    aily
    -0.14
     Leban
    -0.14
    tridge
    -0.14
     cum
    -0.14
    alice
    -0.14
    precated
    -0.13
    Raw
    -0.13
    ÐļТ
    -0.13
    POSITIVE LOGITS
     exactly
    0.18
    834
    0.18
    abwe
    0.17
    exact
    0.17
     exact
    0.17
    kest
    0.17
     precisely
    0.15
    asil
    0.14
    ForObject
    0.14
     âĨĴ↵↵
    0.14
    Act Density 0.282%

    No Known Activations