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

    Neuronpedia

    INDEX
    Explanations

    negations and words indicating uncertainty or disagreement

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

    Followed by "not"

    np_acts-logits-general · gemini-2.0-flash

    not followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſeveral
    -0.94
     myſelf
    -0.94
     Baillargeon
    -0.89
     Efq
    -0.88
     Houſe
    -0.81
     Jefus
    -0.80
     Administrativna
    -0.80
     purpoſe
    -0.79
     bershka
    -0.78
     nahilalakip
    -0.78
    POSITIVE LOGITS
     easy
    0.58
     even
    0.57
     pri
    0.55
    vium
    0.54
     true
    0.52
     pre
    0.51
     fair
    0.50
     c
    0.50
     Even
    0.50
    ो
    0.49
    Act Density 0.220%

    No Known Activations