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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the concept of change over time or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uddenly
    -0.24
     suddenly
    -0.24
     sudden
    -0.21
     Suddenly
    -0.18
     sofort
    -0.18
    Suddenly
    -0.18
     instantly
    -0.17
     immediately
    -0.17
     initially
    -0.17
     already
    -0.17
    POSITIVE LOGITS
    ities
    0.21
    /current
    0.20
    s
    0.19
    mente
    0.18
     succ
    0.17
    arily
    0.17
    idades
    0.16
    succ
    0.16
    ized
    0.15
     resort
    0.15
    Act Density 0.057%

    No Known Activations