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

    Neuronpedia

    INDEX
    Explanations

    words associated with uncertainty or questionable situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gall
    -0.17
    builtin
    -0.15
    heimer
    -0.14
    aris
    -0.14
    lä
    -0.14
    erland
    -0.14
    екÑĤ
    -0.14
     Brig
    -0.14
    poon
    -0.13
    erosis
    -0.13
    POSITIVE LOGITS
    ãģ°ãģĭãĤĬ
    0.18
    ÑĢай
    0.16
    æĦıæĢĿ
    0.16
    zsche
    0.15
    _tolerance
    0.15
    endor
    0.15
    ç¼
    0.14
    trl
    0.14
    picker
    0.14
    OSH
    0.14
    Act Density 0.001%

    No Known Activations