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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values and organization of numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trl
    -0.17
    lemn
    -0.15
    aurus
    -0.15
    ignet
    -0.15
    ramer
    -0.15
     Vert
    -0.15
    erras
    -0.15
     æ¥Ń
    -0.14
    OPS
    -0.14
    ä¸ļ
    -0.14
    POSITIVE LOGITS
    eyer
    0.16
    ilis
    0.14
     Marilyn
    0.14
     Lod
    0.14
     honors
    0.14
    stery
    0.13
    .shtml
    0.13
    ocup
    0.13
    ulet
    0.13
     lim
    0.13
    Act Density 0.001%

    No Known Activations