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

    Neuronpedia

    INDEX
    Explanations

    keywords related to reports and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    references to reports and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zone
    -0.79
    Ability
    -0.77
    ukong
    -0.75
     zones
    -0.75
     populations
    -0.75
    dimension
    -0.73
     Regions
    -0.73
    rises
    -0.73
    zzle
    -0.72
     Abilities
    -0.72
    POSITIVE LOGITS
     authored
    1.13
     titled
    1.08
     satire
    1.06
     informative
    1.06
     published
    1.04
     plagiar
    1.04
     autobi
    1.02
     scathing
    0.99
     reprinted
    0.99
     publication
    0.99
    Act Density 0.626%

    No Known Activations