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

    Neuronpedia

    INDEX
    Explanations

    references to interdisciplinary academic programs and research across various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roid
    -0.16
    ullo
    -0.15
    olle
    -0.15
    erable
    -0.15
     Hir
    -0.15
     Freeze
    -0.14
    SELL
    -0.14
    Ī
    -0.14
    Æ°a
    -0.14
    oted
    -0.13
    POSITIVE LOGITS
     areas
    0.18
    izon
    0.16
    areas
    0.15
    /topic
    0.15
    _areas
    0.15
     cargo
    0.15
     Areas
    0.15
    /modules
    0.15
    dcc
    0.14
    -specific
    0.14
    Act Density 0.177%

    No Known Activations