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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and procedural matters

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and expressions of sentiment or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Newsletter
    -0.62
    ital
    -0.61
     enhances
    -0.61
     Enh
    -0.60
     measurable
    -0.59
    amiliar
    -0.59
    reetings
    -0.59
    democratic
    -0.57
    avorable
    -0.57
    levant
    -0.57
    POSITIVE LOGITS
     resorted
    1.40
     consequently
    1.03
     therefore
    1.02
     instead
    1.00
     blame
    0.98
     stranded
    0.97
     unable
    0.95
     unus
    0.94
     blamed
    0.92
     blames
    0.92
    Act Density 0.536%

    No Known Activations