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

    Neuronpedia

    INDEX
    Explanations

    terms related to membership and organizational structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iks
    -0.17
    ippo
    -0.17
    IRO
    -0.16
    angs
    -0.15
    oom
    -0.15
    bach
    -0.15
     perman
    -0.15
    309
    -0.14
    наÑĩала
    -0.14
    iro
    -0.14
    POSITIVE LOGITS
     mes
    0.15
    adem
    0.15
    iping
    0.15
    æļ
    0.15
    isman
    0.15
    mes
    0.15
    /tutorial
    0.14
    ythe
    0.14
     Nos
    0.14
    má
    0.14
    Act Density 0.455%

    No Known Activations