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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their statements or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supposedly
    -0.90
     reportedly
    -0.89
     apparently
    -0.88
     Apparently
    -0.86
    apparently
    -0.85
     allegedly
    -0.82
    Apparently
    -0.81
     according
    -0.81
    according
    -0.81
     menurut
    -0.80
    POSITIVE LOGITS
     never
    0.66
     aldri
    0.64
     sengaja
    0.61
     kiệm
    0.59
    intention
    0.59
    之所以
    0.56
     nunca
    0.56
     aspetta
    0.55
    つもり
    0.54
     siente
    0.53
    Act Density 0.303%

    No Known Activations