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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortho
    -0.16
    jam
    -0.15
    è¾
    -0.15
    ronym
    -0.15
    Transactional
    -0.14
    lyph
    -0.14
    Normalization
    -0.14
    etsk
    -0.14
    _cube
    -0.14
    _boost
    -0.13
    POSITIVE LOGITS
    cancel
    0.19
    angan
    0.15
     Pedro
    0.15
    Cancel
    0.14
    ÑĥлÑİ
    0.14
     cancel
    0.14
    aris
    0.14
    áÄį
    0.14
    afka
    0.13
    utor
    0.13
    Act Density 0.064%

    No Known Activations