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

    Neuronpedia

    INDEX
    Explanations

    conjunctions indicating contrast or exceptions in statements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.60
    Filmographie
    -0.60
     مرئيه
    -0.59
     nakalista
    -0.58
    LabelTagHelper
    -0.57
     voudrais
    -0.57
    Pyx
    -0.54
    êng
    -0.54
     Italijanski
    -0.54
     समीक्षक
    -0.52
    POSITIVE LOGITS
    </thead>
    0.59
     honor
    0.47
    enumi
    0.46
    eningen
    0.46
    akos
    0.46
    ècie
    0.46
     Gehir
    0.45
    发表于
    0.44
    AppComponent
    0.44
    okay
    0.44
    Act Density 0.053%

    No Known Activations