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

    Neuronpedia

    INDEX
    Explanations

    expressions of limitations or prohibitions

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

    negation or exclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.44
    帖最后由
    -0.41
     lenker
    -0.41
    ebbe
    -0.38
     "..\..\..\
    -0.38
    HasIndex
    -0.36
    ueba
    -0.35
    ⤹
    -0.34
     interesar
    -0.33
    rbp
    -0.33
    POSITIVE LOGITS
    ſelves
    0.62
     createSprite
    0.57
     themſelves
    0.54
     Diſ
    0.54
     ſta
    0.52
    ypeł
    0.51
    ſelf
    0.51
    :✨
    0.50
     Jefus
    0.49
     itſelf
    0.48
    Act Density 0.102%

    No Known Activations