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

    Neuronpedia

    INDEX
    Explanations

    instances of potential or conditional statements and supporting phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sag
    -0.16
     Rick
    -0.16
     Rain
    -0.16
    çª
    -0.15
     gri
    -0.15
     Sun
    -0.15
     sag
    -0.15
     Hunger
    -0.15
    ivar
    -0.14
    2
    -0.14
    POSITIVE LOGITS
    ÙĨدÛĮ
    0.16
    èĮĤ
    0.15
    marshal
    0.15
    аÑĢÑĸв
    0.14
    aucoup
    0.14
    rowable
    0.14
     addCriterion
    0.14
    endon
    0.14
    .joda
    0.14
    complexType
    0.14
    Act Density 0.003%

    No Known Activations