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

    Neuronpedia

    INDEX
    Explanations

    words related to physical or material characteristics and properties

    oai_token-act-pair · gpt-3.5-turbo

    references to various properties of materials or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nadu
    -0.71
    icago
    -0.71
    atre
    -0.66
    scl
    -0.65
    overs
    -0.65
     Siem
    -0.64
     Cron
    -0.64
    bone
    -0.62
    ACTED
    -0.62
     Twins
    -0.62
    POSITIVE LOGITS
     properties
    0.90
    ality
    0.82
    Changed
    0.82
    properties
    0.80
    ious
    0.79
    ually
    0.79
    istry
    0.78
    uation
    0.76
    perties
    0.75
    ally
    0.74
    Act Density 0.042%

    No Known Activations