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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comprehension or empathy

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing comprehension or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rock
    -0.80
    ifact
    -0.77
    rouse
    -0.75
    gins
    -0.70
    inse
    -0.69
    etheus
    -0.67
    etry
    -0.66
    Ranked
    -0.64
    rentice
    -0.63
    ibur
    -0.63
    POSITIVE LOGITS
     MEP
    0.69
    ances
    0.68
    displayText
    0.65
     LF
    0.65
     Duc
    0.64
     sshd
    0.64
    soType
    0.63
     ADC
    0.63
     Norwich
    0.61
    ĺħ
    0.61
    Act Density 0.047%

    No Known Activations