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

    Neuronpedia

    INDEX
    Explanations

    words related to professions or roles, such as developer, candidate, person, worker, insider, investor, politician, journalist, customer, and consumer

    oai_token-act-pair · gpt-3.5-turbo

    references to specific roles or identities of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irens
    -0.85
    ernels
    -0.78
    metadata
    -0.72
    ories
    -0.67
    acements
    -0.67
    ummies
    -0.66
    atars
    -0.65
     Horses
    -0.65
    escription
    -0.64
    clusions
    -0.64
    POSITIVE LOGITS
     learns
    1.31
     chooses
    1.31
     knows
    1.16
     decides
    1.10
     spends
    1.09
     wants
    1.07
     understands
    1.07
     behaves
    1.06
     earns
    1.05
     enjoys
    1.05
    Act Density 0.181%

    No Known Activations