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

    Neuronpedia

    INDEX
    Explanations

    negation and related qualifiers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldorf
    -0.15
    veau
    -0.14
     Verfüg
    -0.14
    ousel
    -0.13
     éħ
    -0.13
    ire
    -0.13
    ستÙħ
    -0.13
     Tw
    -0.13
    å¥ı
    -0.13
    ired
    -0.13
    POSITIVE LOGITS
     domic
    0.15
    SystemService
    0.15
     Pemb
    0.14
    _FATAL
    0.14
    ì±Ħ
    0.14
    iferay
    0.14
     Mec
    0.14
    741
    0.14
    UCE
    0.14
    847
    0.13
    Act Density 0.150%

    No Known Activations