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

    Neuronpedia

    INDEX
    Explanations

    phrases involving approximate quantities or estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orum
    -0.16
     punch
    -0.14
     iceberg
    -0.14
     stag
    -0.13
    atrix
    -0.13
    cess
    -0.13
     вÑģего
    -0.13
    ī
    -0.13
     Mist
    -0.13
     Karn
    -0.13
    POSITIVE LOGITS
    agna
    0.16
    ¦¬
    0.16
    nid
    0.15
    stown
    0.15
    olute
    0.15
    groundColor
    0.15
    ãĥ¼ãĥĢ
    0.14
    amba
    0.14
    anges
    0.14
    ÏĮν
    0.14
    Act Density 0.009%

    No Known Activations