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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -Language
    -0.15
     Alphabet
    -0.15
    äºķ
    -0.15
    visible
    -0.15
    ekk
    -0.14
     Bien
    -0.14
    othy
    -0.14
    ostel
    -0.14
     Bray
    -0.14
    .dev
    -0.13
    POSITIVE LOGITS
     usage
    0.18
    588
    0.16
    _tensors
    0.15
    \common
    0.15
    strar
    0.14
    285
    0.14
    usage
    0.14
     valide
    0.14
    æ
    0.13
    ipel
    0.13
    Act Density 0.027%

    No Known Activations