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

    Neuronpedia

    INDEX
    Explanations

    mentions of actions being taken or decisions being made by someone

    oai_token-act-pair · gpt-3.5-turbo

    narratives about challenges and resolutions in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ³³³³³³³³³³³³³³³³
    -0.71
    >>>>>>>>
    -0.70
    âĢ
    -0.69
    His
    -0.68
    ã
    -0.68
    ´
    -0.68
     âĢ
    -0.68
    izons
    -0.66
    )</
    -0.66
    ende
    -0.66
    POSITIVE LOGITS
     themselves
    1.29
     their
    1.19
     theirs
    1.13
    their
    1.04
     THEIR
    1.00
     they
    0.92
     Their
    0.77
    Their
    0.75
    they
    0.72
     apiece
    0.71
    Act Density 0.832%

    No Known Activations