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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associated contexts within sentences

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

    Follows commas or introduces quotations

    np_acts-logits-general · gemini-2.0-flash

    Selective coupling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unknownFields
    -0.80
    findpost
    -0.74
    ContentAsync
    -0.72
    )++;
    -0.71
     esternos
    -0.69
    
    -0.69
    KommentareTeilen
    -0.68
    contentLoaded
    -0.68
     hefyd
    -0.67
     CreateTagHelper
    -0.67
    POSITIVE LOGITS
     according
    1.02
    according
    0.80
    According
    0.67
     menurut
    0.65
     said
    0.64
     según
    0.64
     selon
    0.64
     officials
    0.60
    said
    0.59
     volgens
    0.55
    Act Density 0.123%

    No Known Activations