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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences ending with conjunctions/transition words

    np_acts-logits-general · gemini-2.0-flash

    contrastive sentence starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GeneratedValue
    -0.80
    IContainer
    -0.79
    Autoritní
    -0.74
    +#+#
    -0.72
     Exactos
    -0.70
    writeFieldEnd
    -0.69
    dolu
    -0.65
    UseVisualStyle
    -0.65
    AddTagHelper
    -0.64
    WebElementEntity
    -0.59
    POSITIVE LOGITS
    Nevertheless
    1.63
     Nevertheless
    1.60
     nevertheless
    1.49
    Nonetheless
    1.47
     Nonetheless
    1.47
     but
    1.46
     Fortunately
    1.36
    Fortunately
    1.32
    but
    1.27
     nonetheless
    1.26
    Act Density 0.554%

    No Known Activations