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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INUX
    -0.18
    unde
    -0.16
    isco
    -0.16
    js
    -0.15
    ks
    -0.15
    ä¸Ģ级
    -0.15
    ipse
    -0.15
    _EXPORT
    -0.14
    untime
    -0.14
    ãĥªãĥ³
    -0.14
    POSITIVE LOGITS
     bulk
    0.23
     majority
    0.21
     volumes
    0.20
    bulk
    0.18
    uant
    0.17
    -volume
    0.17
     quantities
    0.17
     volume
    0.16
    .volume
    0.16
     Volume
    0.16
    Act Density 0.005%

    No Known Activations