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

    Neuronpedia

    INDEX
    Explanations

    phrases related to law enforcement and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lasts
    -0.75
    izable
    -0.73
    acters
    -0.72
     occurs
    -0.70
     Telesc
    -0.68
    ossom
    -0.68
     belongs
    -0.67
    owan
    -0.65
     fades
    -0.64
    atural
    -0.64
    POSITIVE LOGITS
     hoping
    1.23
     aware
    1.09
     currently
    1.09
     pleased
    1.08
     adamant
    1.06
     glad
    1.06
     expecting
    1.03
     planning
    1.02
     confident
    1.00
     now
    1.00
    Act Density 0.315%

    No Known Activations