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

    Neuronpedia

    INDEX
    Explanations

    references to panel discussions and expert contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibold
    -0.17
    nbr
    -0.15
    ân
    -0.14
    istrovstvÃŃ
    -0.14
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.14
    asons
    -0.14
    TRS
    -0.14
    Backing
    -0.14
    ½æķ°
    -0.14
    imei
    -0.14
    POSITIVE LOGITS
    ìĮ
    0.15
    ltk
    0.15
    046
    0.14
    058
    0.14
    ModelError
    0.14
    _chance
    0.14
    726
    0.14
     Eig
    0.13
     Eddie
    0.13
     Rut
    0.13
    Act Density 0.057%

    No Known Activations