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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "nothing" or "nothingness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mont
    -0.16
    agli
    -0.14
    าà¸ĩ
    -0.14
    ãĤ¥
    -0.14
    assing
    -0.14
     Ost
    -0.14
    iano
    -0.14
     somehow
    -0.13
    azor
    -0.13
    uda
    -0.13
    POSITIVE LOGITS
     else
    0.29
    ness
    0.26
    else
    0.24
    burger
    0.20
    Else
    0.19
    NESS
    0.18
    _else
    0.17
     Else
    0.16
     ELSE
    0.16
    ennes
    0.16
    Act Density 0.037%

    No Known Activations