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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software development and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollapse
    -0.18
    leurs
    -0.16
    terdam
    -0.15
    769
    -0.15
    ipe
    -0.15
    enga
    -0.14
    á»ĵi
    -0.14
     cl
    -0.14
    erville
    -0.14
    elerik
    -0.14
    POSITIVE LOGITS
    ÑĨем
    0.14
     arena
    0.14
    agt
    0.14
     tolerate
    0.14
    ares
    0.14
    inel
    0.14
    iang
    0.13
    eÄį
    0.13
    ÑĨÑĸ
    0.13
    gram
    0.13
    Act Density 0.085%

    No Known Activations