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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of people or places with a specific pattern "Ath" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific athlete or team name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Charge
    -0.73
    BOX
    -0.72
     Reloaded
    -0.68
     Pupp
    -0.68
     Zucker
    -0.68
     externalToEVAOnly
    -0.68
    ãģ®éŃĶ
    -0.67
     Showtime
    -0.67
     Gemini
    -0.67
     Canaver
    -0.66
    POSITIVE LOGITS
    lete
    1.01
     Ath
    1.00
    saf
    0.95
    onite
    0.91
    viation
    0.90
    assian
    0.86
    itud
    0.85
     unden
    0.84
    itudes
    0.83
    anasia
    0.82
    Act Density 0.008%

    No Known Activations