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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "tough."

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

    tough situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fileID
    -0.52
    //
    -0.52
    appé
    -0.49
     alis
    -0.45
    HasAnnotation
    -0.45
    ▣
    -0.44
    {{/
    -0.44
    +#+
    -0.42
    cidae
    -0.42
    |')
    -0.41
    POSITIVE LOGITS
     tough
    2.05
    Tough
    2.00
     Tough
    2.00
    tough
    1.99
     tougher
    1.67
     toughest
    1.63
     toughness
    1.45
     tuff
    1.02
     Tuff
    0.96
     hård
    0.85
    Act Density 0.004%

    No Known Activations