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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating or introducing the speaker's thoughts

    oai_token-act-pair · gpt-3.5-turbo

    phrases conveying doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawled
    -0.75
    yna
    -0.64
    ouls
    -0.62
    oubted
    -0.62
    ãĤ´ãĥ³
    -0.61
    mpeg
    -0.60
    ufact
    -0.60
    è»
    -0.60
    omics
    -0.60
    aid
    -0.60
    POSITIVE LOGITS
     anymore
    1.02
     anything
    0.94
     anybody
    0.91
     whatsoever
    0.90
     anyone
    0.84
     nor
    0.83
     any
    0.78
     necessarily
    0.77
     anywhere
    0.75
     exactly
    0.70
    Act Density 0.057%

    No Known Activations