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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing worthiness or deservingness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of worthiness or merit in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¦ãĤ¹
    -0.77
    ullivan
    -0.76
    alsa
    -0.69
    wi
    -0.68
    laws
    -0.67
    strate
    -0.67
    ettle
    -0.67
    hiba
    -0.65
    miah
    -0.64
    aha
    -0.63
    POSITIVE LOGITS
     attention
    1.36
     scrutiny
    1.36
     consideration
    1.34
     inclusion
    1.32
     mention
    1.21
     designation
    1.06
     recognition
    1.04
     scorn
    1.03
     condemnation
    1.00
     praise
    1.00
    Act Density 0.207%

    No Known Activations