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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference original artistic works or creations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     originally
    -0.21
     initially
    -0.20
    Originally
    -0.18
     Originally
    -0.18
    origin
    -0.17
    original
    -0.16
    additional
    -0.16
    سÙĪب
    -0.16
    initial
    -0.16
     inicial
    -0.15
    POSITIVE LOGITS
    ity
    0.54
    ITY
    0.33
     intent
    0.32
     intention
    0.29
    ities
    0.26
    y
    0.25
    mente
    0.25
     Intent
    0.24
     intentions
    0.24
    intent
    0.23
    Act Density 0.038%

    No Known Activations