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

    Neuronpedia

    INDEX
    Explanations

    food-related adjectives and descriptive phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <=",
    -0.64
    Sempre
    -0.60
     Sempre
    -0.58
     @"";
    -0.55
     dále
    -0.53
     tarko
    -0.52
    DoubleQuotes
    -0.52
     dunque
    -0.52
    Inflater
    -0.50
    Always
    -0.50
    POSITIVE LOGITS
     even
    1.53
     sogar
    1.51
     zelfs
    1.49
     addirittura
    1.37
    even
    1.36
     persino
    1.34
     almost
    1.30
    Bahkan
    1.25
     Bahkan
    1.24
     даже
    1.23
    Act Density 0.579%

    No Known Activations