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

    Neuronpedia

    INDEX
    Explanations

    events or actions described in a narrative or story

    oai_token-act-pair · gpt-3.5-turbo

    affirmative phrases or expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Additionally
    -0.88
     Additionally
    -0.80
    RELATED
    -0.78
    Currently
    -0.77
    gaming
    -0.77
     advancements
    -0.76
     eSports
    -0.75
    Trend
    -0.74
     Currently
    -0.74
     fueling
    -0.72
    POSITIVE LOGITS
     humour
    0.97
     ..."
    0.92
     poems
    0.90
     trousers
    0.90
     doubtless
    0.86
     Tolkien
    0.83
     poem
    0.81
     manuscript
    0.81
     envis
    0.80
     Auschwitz
    0.79
    Act Density 1.747%

    No Known Activations