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

    Neuronpedia

    INDEX
    Explanations

    narratives or storytelling elements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    narrative prose describing characters' actions or movements in a story.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @eekay

    Narrative text describing characters, their actions, and relationships, particularly focusing on royalty, authority figures, and social interactions in formal settings.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @eekay
    New Auto-Interp
    Negative Logits
     patin
    -0.94
     bombe
    -0.92
     satel
    -0.90
     lapto
    -0.86
     vola
    -0.84
     ristor
    -0.84
     anse
    -0.84
     prostitu
    -0.83
     boxe
    -0.82
     venez
    -0.82
    POSITIVE LOGITS
     McLaugh
    1.79
     McInt
    1.65
     Vaugh
    1.49
     Bartholo
    1.40
     Daven
    1.39
     unlaw
    1.38
     Cuth
    1.35
     Rine
    1.32
     Gorb
    1.29
     Rodrig
    1.29
    Act Density 0.640%

    No Known Activations