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

    Neuronpedia

    INDEX
    Explanations

    references to business and wealth-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erb
    -0.15
    alue
    -0.15
    ãģłãģijãģ©
    -0.14
     Sesso
    -0.14
    robat
    -0.14
    edeki
    -0.14
     Calories
    -0.13
    ameleon
    -0.13
    roys
    -0.13
    onto
    -0.13
    POSITIVE LOGITS
     allegedly
    0.86
     reportedly
    0.74
     supposedly
    0.70
     alleged
    0.61
     apparently
    0.60
     according
    0.58
     purported
    0.57
     supposed
    0.54
     Apparently
    0.51
     According
    0.48
    Act Density 0.629%

    No Known Activations