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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and references to statutory provisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.79
    TagMode
    -0.64
    encodeWith
    -0.60
     चीज़ों
    -0.59
    kloped
    -0.56
     mergeFrom
    -0.56
    הערות
    -0.54
     ProtoMessage
    -0.54
     Taktlose
    -0.53
     himo
    -0.52
    POSITIVE LOGITS
     feroit
    0.75
     houſe
    0.74
     auroit
    0.70
     enfans
    0.67
     prêtres
    0.67
     sicura
    0.66
     ſtate
    0.66
     étoit
    0.66
     pleaſure
    0.65
     tarko
    0.64
    Act Density 0.441%

    No Known Activations