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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "strong" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upaten
    -0.71
    atimes
    -0.70
     Maus
    -0.70
    kaido
    -0.69
    AccessException
    -0.66
    Datuak
    -0.63
     oblivion
    -0.63
     délib
    -0.63
    Loot
    -0.62
     felizes
    -0.62
    POSITIVE LOGITS
     Strong
    1.45
    strong
    1.45
    STRONG
    1.41
    Strong
    1.38
     STRONG
    1.38
     strong
    1.31
    strength
    1.30
    ngths
    1.25
     strength
    1.21
    Strength
    1.20
    Act Density 0.085%

    No Known Activations