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

    Neuronpedia

    INDEX
    Explanations

    verbs in present or past tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant moments or experiences in personal narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enfranch
    -0.91
    DNA
    -0.82
    arations
    -0.80
    vier
    -0.73
     democrat
    -0.68
    illusion
    -0.67
    edom
    -0.67
    equality
    -0.67
    iant
    -0.66
    yet
    -0.66
    POSITIVE LOGITS
     gatherings
    1.02
     dinners
    0.95
     specials
    0.93
     mornings
    0.91
     banter
    0.87
     evenings
    0.87
     chats
    0.85
     meetings
    0.85
     reminders
    0.84
     jams
    0.83
    Act Density 0.737%

    No Known Activations