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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical or abstract characteristics or attributes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various properties in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nadu
    -0.79
    icago
    -0.74
     Cortex
    -0.66
    atre
    -0.65
    ansen
    -0.63
     Siem
    -0.63
     Cron
    -0.61
    bone
    -0.61
    ways
    -0.61
    ACTED
    -0.61
    POSITIVE LOGITS
     properties
    0.92
    ality
    0.91
    properties
    0.85
    uation
    0.84
    Changed
    0.80
    ually
    0.80
    ious
    0.78
    iveness
    0.77
    istry
    0.76
    ally
    0.75
    Act Density 0.045%

    No Known Activations