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

    Neuronpedia

    INDEX
    Explanations

    concepts related to scientific explanations and theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     laut
    -0.16
    vik
    -0.15
    ork
    -0.15
    _SRV
    -0.14
    shire
    -0.14
    æ
    -0.14
    ëįĺ
    -0.14
    illis
    -0.13
    sg
    -0.13
     nab
    -0.13
    POSITIVE LOGITS
     observed
    0.18
     why
    0.18
     Formation
    0.18
    ãģıãĤĵ
    0.17
    Formation
    0.16
    unami
    0.16
    kün
    0.16
     mystery
    0.16
     formation
    0.15
    isbury
    0.15
    Act Density 0.289%

    No Known Activations