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

    Neuronpedia

    INDEX
    Explanations

    structure and formatting related to research documents or technical writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     either
    -0.63
     such
    -0.61
     Additionally
    -0.58
     aforementioned
    -0.58
    ViewFeatures
    -0.57
    Additionally
    -0.57
     somewhat
    -0.56
     which
    -0.54
     altogether
    -0.54
     fameux
    -0.54
    POSITIVE LOGITS
     :
    0.74
    Havolalar
    0.73
     autorytatywna
    0.73
     kaarangay
    0.68
    ":
    0.66
    boldmath
    0.65
    教你
    0.65
    ?:
    0.64
    '".
    0.63
    verifyException
    0.62
    Act Density 0.716%

    No Known Activations