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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-improvement and personal growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urus
    -0.50
    נוּ
    -0.47
    Bland
    -0.46
    tgärder
    -0.45
     kam
    -0.45
    **/
    -0.45
    glGen
    -0.45
     lemb
    -0.42
    demik
    -0.42
    ناد
    -0.41
    POSITIVE LOGITS
     learning
    0.81
     Valuable
    0.77
     learnings
    0.76
    valuable
    0.73
    learning
    0.73
     valuable
    0.72
     learn
    0.70
     learns
    0.70
     Learning
    0.70
    Learning
    0.70
    Act Density 0.385%

    No Known Activations