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

    Neuronpedia

    INDEX
    Explanations

    instances of input/output identifiers and formatting markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.69
    +#+#
    -0.68
     referenties
    -0.67
    ❸
    -0.63
     Chwiliwch
    -0.58
     sumpay
    -0.55
    chauung
    -0.54
    PHONY
    -0.50
     فريبيس
    -0.49
    次回は
    -0.49
    POSITIVE LOGITS
     rhestr
    1.05
    ⓧ
    1.00
     يتيمه
    0.88
     continúas
    0.82
    Geplaatst
    0.78
    তথ্যসূত্র
    0.77
     مرئيه
    0.76
    TestBed
    0.74
    sizeCache
    0.74
    Skocz
    0.74
    Act Density 0.315%

    No Known Activations