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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors, particularly variations of the word "bad."

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

    negative qualities or situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HasBeenSet
    -0.39
    ⟬
    -0.39
    neath
    -0.36
     hadapan
    -0.36
    UnusedPrivate
    -0.35
    こちらは
    -0.35
     Concern
    -0.34
    thias
    -0.34
    bleshooting
    -0.33
     Concerns
    -0.33
    POSITIVE LOGITS
     bad
    0.85
    bad
    0.71
    Bad
    0.70
     BAD
    0.64
    BAD
    0.61
     Bad
    0.60
     mauvaise
    0.59
     malos
    0.59
     luck
    0.59
     omen
    0.56
    Act Density 0.021%

    No Known Activations