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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to measurements or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agues
    -0.19
    ëĮ
    -0.15
     Kapoor
    -0.15
    plementation
    -0.14
    lon
    -0.14
    ella
    -0.14
    åħµ
    -0.14
    EMP
    -0.13
     Mog
    -0.13
    agina
    -0.12
    POSITIVE LOGITS
    enn
    0.20
    /Dk
    0.16
    olec
    0.16
    DTD
    0.15
     ham
    0.15
     PIPE
    0.15
    antal
    0.15
    endi
    0.15
     Hood
    0.14
    mil
    0.14
    Act Density 0.256%

    No Known Activations