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

    Neuronpedia

    INDEX
    Explanations

    command-like sentences or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey action or decision-making in narrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zbollah
    -0.76
    ahime
    -0.65
    ampions
    -0.62
    adium
    -0.61
     Comprehensive
    -0.60
    ularity
    -0.59
    ishable
    -0.59
     Doomsday
    -0.58
     UNITED
    -0.57
    Brexit
    -0.57
    POSITIVE LOGITS
    upon
    0.82
    Later
    0.73
     then
    0.72
     later
    0.72
     reluctantly
    0.69
     instructed
    0.69
     promptly
    0.69
     startled
    0.65
     astonished
    0.64
     hurried
    0.63
    Act Density 1.004%

    No Known Activations