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

    Neuronpedia

    INDEX
    Explanations

    truths and their complexities within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BorderRadius
    -0.65
    cluye
    -0.63
     noft
    -0.61
    grew
    -0.59
     fusca
    -0.59
     supérieurs
    -0.58
     pères
    -0.57
     schuldig
    -0.57
     adquis
    -0.56
     fizer
    -0.55
    POSITIVE LOGITS
     spoken
    0.95
     played
    0.83
     argued
    0.82
     fought
    0.82
     talked
    0.81
     shouted
    0.81
     uttered
    0.80
     told
    0.80
     whispered
    0.80
     danced
    0.79
    Act Density 0.533%

    No Known Activations