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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghi
    -0.15
     Olson
    -0.14
     Tos
    -0.14
    airie
    -0.14
     Mond
    -0.14
    USH
    -0.14
    Ïĩν
    -0.14
     ÐľÐ¸Ñħай
    -0.14
    enson
    -0.14
    alfa
    -0.13
    POSITIVE LOGITS
     Doom
    0.38
     Beast
    0.26
     Titans
    0.25
     DC
    0.24
     Jane
    0.23
     Cy
    0.23
     Robot
    0.23
     DOE
    0.22
     Patrol
    0.22
     Crazy
    0.22
    Act Density 0.003%

    No Known Activations