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

    Neuronpedia

    INDEX
    Explanations

    words related to entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.72
    strap
    -0.71
    manship
    -0.70
    phrine
    -0.70
     Archangel
    -0.67
    Ø©
    -0.66
     hearts
    -0.64
     Spears
    -0.62
     tremend
    -0.61
    ned
    -0.61
    POSITIVE LOGITS
    ropy
    1.43
    rance
    1.28
    itled
    1.24
    raction
    1.18
    rants
    1.13
    reprene
    1.12
    renched
    1.06
    race
    1.03
    ire
    1.02
    ourage
    0.99
    Act Density 0.006%

    No Known Activations