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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and variables related to statistical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     erotik
    -0.17
    alars
    -0.16
     cháºŃm
    -0.15
     eskort
    -0.15
     RuntimeObject
    -0.14
    .yy
    -0.14
     RuntimeMethod
    -0.14
     addCriterion
    -0.14
     ëĭ¤ìļ´ë°Ľê¸°
    -0.14
    lacak
    -0.13
    POSITIVE LOGITS
    âĢ¦I
    0.18
     [âĢ¦]↵
    0.18
    âĢ¦and
    0.17
    âĢ¦it
    0.17
    âĢ¦the
    0.17
    âĢ¦↵↵
    0.17
    âĢ¦but
    0.16
    âĢ¦↵
    0.16
     âĢ¦↵↵
    0.16
     [âĢ¦
    0.15
    Act Density 0.905%

    No Known Activations