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

    Neuronpedia

    INDEX
    Explanations

    dates and events related to certain activities or statements

    oai_token-act-pair · gpt-3.5-turbo

    specific temporal phrases and contexts related to events or statements made

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usercontent
    -0.67
    amental
    -0.65
    found
    -0.62
    abiding
    -0.62
     Entered
    -0.61
     Divinity
    -0.60
    atonin
    -0.57
    atic
    -0.56
    FIELD
    -0.56
     harms
    -0.56
    POSITIVE LOGITS
     newsp
    0.86
    amera
    0.79
     Azerb
    0.71
     sarcast
    0.69
    éĹ
    0.68
     briefing
    0.68
     Reloaded
    0.67
     introductory
    0.66
    urai
    0.65
     paraph
    0.65
    Act Density 0.211%

    No Known Activations