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

    Neuronpedia

    INDEX
    Explanations

    words related to legal actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of financial or performance-related metrics and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    population
    -0.65
    estro
    -0.62
    resource
    -0.62
     guiIcon
    -0.60
     neighbour
    -0.59
    ãĤ´
    -0.59
     ruler
    -0.59
    always
    -0.59
    othe
    -0.59
    cest
    -0.58
    POSITIVE LOGITS
     respectively
    1.71
     respective
    1.47
     careers
    1.42
     apiece
    1.31
     themselves
    1.31
     roles
    1.19
    selves
    1.11
     departures
    1.07
     their
    1.02
     suspensions
    0.97
    Act Density 0.535%

    No Known Activations