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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    specific proper nouns and entities related to locations, brands, or notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]."
    -0.78
     ..."
    -0.75
    ().
    -0.72
    .�
    -0.72
    }.
    -0.72
    )."
    -0.71
    .).
    -0.70
    )).
    -0.69
    .<
    -0.68
    ¶ħ
    -0.66
    POSITIVE LOGITS
     Facts
    0.64
     Basics
    0.61
     revolves
    0.59
     hinges
    0.57
     boosters
    0.57
     renaissance
    0.56
     basics
    0.56
     Expand
    0.54
     consists
    0.53
    undrum
    0.53
    Act Density 0.771%

    No Known Activations