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

    Neuronpedia

    INDEX
    Explanations

    the word "good" or its synonyms in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of making good or great decisions and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.71
    ngth
    -0.69
    sed
    -0.62
    rouse
    -0.60
    ILA
    -0.60
    ridor
    -0.60
    hran
    -0.60
    ught
    -0.60
     Niet
    -0.60
    eur
    -0.59
    POSITIVE LOGITS
     decisions
    1.07
     choices
    1.03
     strides
    0.94
     sacrifices
    0.89
    ends
    0.83
     adjustments
    0.83
     compromises
    0.81
     distinctions
    0.80
     mistakes
    0.78
     judgments
    0.78
    Act Density 0.063%

    No Known Activations