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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to systems, applications, and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     certainly
    -0.19
     Certainly
    -0.15
    probably
    -0.15
     probably
    -0.15
     Probably
    -0.15
    ará
    -0.14
    ä¸įä¼ļ
    -0.14
     soon
    -0.14
     hereby
    -0.14
    ensure
    -0.13
    POSITIVE LOGITS
     вдÑĢÑĥг
    0.25
     exceeds
    0.23
     is
    0.22
     happens
    0.21
     fails
    0.20
     hasn
    0.20
     or
    0.19
     suddenly
    0.18
     ever
    0.18
     isn
    0.18
    Act Density 0.245%

    No Known Activations