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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers and year references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĽ¢
    -0.15
    578
    -0.14
    ERM
    -0.13
     destructive
    -0.13
    Ñĥв
    -0.13
    ing
    -0.13
    utive
    -0.13
    -âĢIJ
    -0.13
     offset
    -0.13
    o
    -0.13
    POSITIVE LOGITS
    ormsg
    0.16
    ầu
    0.16
    ï¸ı
    0.15
    ocrats
    0.14
    (æľ¨
    0.14
    ypse
    0.14
    ether
    0.14
    'gc
    0.14
    ipeg
    0.13
     Äijá»Ŀi
    0.13
    Act Density 0.054%

    No Known Activations