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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reported information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reportedly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acles
    -0.70
    arity
    -0.64
    ween
    -0.62
    erest
    -0.60
    thing
    -0.60
    ento
    -0.60
     faire
    -0.58
    ente
    -0.58
    acle
    -0.57
    olon
    -0.57
    POSITIVE LOGITS
     reportedly
    3.44
     allegedly
    2.32
     purportedly
    2.07
     apparently
    1.84
     supposedly
    1.81
     presumably
    1.61
     evidently
    1.55
     rumored
    1.51
     famously
    1.46
     ostensibly
    1.39
    Act Density 0.014%

    No Known Activations