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

    Neuronpedia

    INDEX
    Explanations

    references to research and academic analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irie
    -0.22
    wie
    -0.16
    PPER
    -0.14
    ardown
    -0.13
     cons
    -0.13
    ulas
    -0.13
    _lazy
    -0.13
    \admin
    -0.13
    aras
    -0.13
    dao
    -0.13
    POSITIVE LOGITS
     Outputs
    0.15
    DEPTH
    0.15
    preh
    0.15
    ¥
    0.14
     forsk
    0.14
    ero
    0.14
     depth
    0.14
    anova
    0.14
    oid
    0.14
    Subjects
    0.14
    Act Density 0.002%

    No Known Activations