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

    Neuronpedia

    INDEX
    Explanations

    actions or opinions taken or expressed quickly or promptly

    oai_token-act-pair · gpt-3.5-turbo

    instances of quick or prompt actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decay
    -0.83
     generational
    -0.77
     immortality
    -0.77
     attainment
    -0.74
     transformation
    -0.74
     continuum
    -0.72
     transitions
    -0.72
     transformations
    -0.72
     vitality
    -0.71
     loneliness
    -0.71
    POSITIVE LOGITS
     applaud
    0.96
     impressed
    0.92
    warn
    0.88
     cautioned
    0.86
     worried
    0.85
     keen
    0.85
     alerted
    0.85
     amazed
    0.85
     amused
    0.84
     delighted
    0.84
    Act Density 0.602%

    No Known Activations