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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the absence or lack of something

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

    absence of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.52
    ReusableCell
    -0.49
     foto
    -0.47
    featureID
    -0.45
    rungsseite
    -0.44
    inaison
    -0.43
    bootstrapcdn
    -0.42
     broadest
    -0.41
     erbjud
    -0.41
    guiente
    -0.40
    POSITIVE LOGITS
    帖最后由
    0.61
     without
    0.47
    Without
    0.46
    without
    0.45
    Requires
    0.45
     WITHOUT
    0.44
     Without
    0.43
    GIVEREF
    0.43
     needing
    0.42
    Needs
    0.42
    Act Density 0.024%

    No Known Activations