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

    Neuronpedia

    INDEX
    Explanations

    interesting and diverse topics, from books and literature critiques to political statements and scientific discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     referen
    -0.62
    umerous
    -0.61
     customary
    -0.61
     brush
    -0.59
     combination
    -0.59
     foreground
    -0.58
     inhibitor
    -0.58
     muted
    -0.58
     inclined
    -0.57
     spurious
    -0.57
    POSITIVE LOGITS
     Lives
    0.91
     Matters
    0.91
     Dreams
    0.90
     Secrets
    0.89
     Yourself
    0.89
     Strategies
    0.88
     Lies
    0.87
     Madness
    0.87
     Files
    0.86
     Tomorrow
    0.85
    Act Density 0.471%

    No Known Activations