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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating interest, excitement, evaluation or speculation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotions or impactful statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertisement
    -0.59
    sheet
    -0.59
     culture
    -0.58
    Attribute
    -0.57
    athi
    -0.57
    Connector
    -0.56
    Numbers
    -0.55
    ugh
    -0.55
     allegedly
    -0.55
     supposedly
    -0.54
    POSITIVE LOGITS
     someday
    1.07
     tomorrow
    1.06
     sooner
    0.86
    morrow
    0.84
     forever
    0.81
     hereafter
    0.76
     wiser
    0.75
     soon
    0.73
     anytime
    0.72
     next
    0.72
    Act Density 0.882%

    No Known Activations