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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords such as 'import', 'class', and 'var'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.14
    analytics
    -0.14
    esh
    -0.13
    .har
    -0.13
    bsp
    -0.13
    ikh
    -0.13
    anooga
    -0.13
    kening
    -0.13
    hive
    -0.13
    lass
    -0.13
    POSITIVE LOGITS
    utsch
    0.15
    asInstanceOf
    0.14
    umo
    0.14
    ulace
    0.14
    duto
    0.14
    ãģ¡ãģ¯
    0.14
    jee
    0.14
     conver
    0.14
    elic
    0.13
     float
    0.13
    Act Density 0.003%

    No Known Activations