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

    Neuronpedia

    INDEX
    Explanations

    references to diagrams and figures related to technical content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enant
    -0.17
    obus
    -0.15
    PHA
    -0.14
    Uvs
    -0.14
    verage
    -0.14
    ante
    -0.14
    umbnails
    -0.14
     ëĭ¤ìļ´ë°Ľê¸°
    -0.14
    ighthouse
    -0.13
    OrFail
    -0.13
    POSITIVE LOGITS
    alink
    0.15
    ERS
    0.14
    дÑĢеÑģ
    0.14
    ħn
    0.14
    ers
    0.13
    chn
    0.13
     Voy
    0.13
    Exc
    0.13
     Bias
    0.13
    variable
    0.13
    Act Density 0.067%

    No Known Activations