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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical or temporal information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑĢд
    -0.16
    erre
    -0.15
    ithub
    -0.15
    ioxid
    -0.15
    785
    -0.15
    imer
    -0.14
    ettle
    -0.14
    inka
    -0.14
     Truy
    -0.14
    .li
    -0.14
    POSITIVE LOGITS
    eam
    0.16
    _AUX
    0.15
    imo
    0.15
     Cassidy
    0.14
    TURE
    0.14
    ovnÃŃ
    0.14
    asures
    0.14
    ead
    0.13
    wiki
    0.13
     abstract
    0.13
    Act Density 0.003%

    No Known Activations