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

    Neuronpedia

    INDEX
    Explanations

    references to committees and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abei
    -0.16
    iferay
    -0.16
    ifting
    -0.15
    icom
    -0.15
    cef
    -0.14
    yc
    -0.14
     поÑĤ
    -0.14
    èªī
    -0.14
     trá»±c
    -0.13
    akt
    -0.13
    POSITIVE LOGITS
    ears
    0.18
     Tart
    0.15
    inline
    0.15
    /state
    0.14
     Conrad
    0.14
    pras
    0.14
    rons
    0.13
    _Collections
    0.13
    zens
    0.13
    TL
    0.13
    Act Density 0.018%

    No Known Activations