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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "something."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isch
    -0.15
    ric
    -0.15
    oug
    -0.14
    à¸ŀà¸Ń
    -0.14
    sync
    -0.14
     ones
    -0.14
    aland
    -0.14
    ÚĨÙĩ
    -0.14
     somehow
    -0.13
     mere
    -0.13
    POSITIVE LOGITS
     else
    0.33
    else
    0.24
    _else
    0.22
    Else
    0.21
     ELSE
    0.20
    	else
    0.19
     substantial
    0.18
     concrete
    0.17
     special
    0.17
    ELSE
    0.17
    Act Density 0.100%

    No Known Activations