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

    Neuronpedia

    INDEX
    Explanations

    phrases related to talent or performance at various levels or positions

    oai_token-act-pair · gpt-3.5-turbo

    references to performance levels and capabilities in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rely
    -0.72
     NEWS
    -0.70
    zzle
    -0.69
    arthed
    -0.67
    vati
    -0.66
     Bans
    -0.65
    pour
    -0.64
    warn
    -0.62
    zik
    -0.60
    bys
    -0.60
    POSITIVE LOGITS
     level
    1.23
     caliber
    1.11
     collegiate
    1.07
     age
    1.03
     position
    1.02
    Level
    1.02
    NBA
    0.97
     levels
    0.96
     skill
    0.94
     stature
    0.91
    Act Density 0.132%

    No Known Activations