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

    Neuronpedia

    INDEX
    Explanations

    terms related to moral excellence or goodness

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "virtue."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oths
    -0.70
    PsyNetMessage
    -0.69
    gdala
    -0.69
    WER
    -0.68
    stretched
    -0.68
    sites
    -0.68
    è¦ļéĨĴ
    -0.67
    oval
    -0.67
    ockets
    -0.66
    AMI
    -0.65
    POSITIVE LOGITS
     Virtue
    0.90
     virtue
    0.89
    uous
    0.88
    ocracy
    0.84
     signalling
    0.82
    ocratic
    0.77
     signaling
    0.77
    ously
    0.75
    iencies
    0.71
    ionage
    0.71
    Act Density 0.017%

    No Known Activations