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

    Neuronpedia

    INDEX
    Explanations

    references to the potential and implications of various phenomena, particularly in health and biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     presumably
    -0.75
     supposedly
    -0.72
     allegedly
    -0.72
     purported
    -0.69
     alleged
    -0.67
     apparently
    -0.66
     ostensibly
    -0.66
     presumed
    -0.64
     schein
    -0.64
     reportedly
    -0.63
    POSITIVE LOGITS
     outcomes
    0.84
     outcome
    0.83
    outcome
    0.82
     future
    0.81
    future
    0.78
     تضيفلها
    0.77
     pitfalls
    0.71
    hood
    0.70
     Outcomes
    0.70
    mente
    0.69
    Act Density 0.453%

    No Known Activations