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

    Neuronpedia

    INDEX
    Explanations

    instances where there is interaction or conflict between multiple entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of conflict or interaction between parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pees
    -0.72
    uve
    -0.63
    appa
    -0.62
    vier
    -0.61
    arna
    -0.61
     Metatron
    -0.59
    usa
    -0.57
    icut
    -0.57
    wcs
    -0.57
    agle
    -0.56
    POSITIVE LOGITS
    other
    1.91
     other
    1.74
     others
    1.47
     OTHER
    1.40
     Other
    1.33
    another
    1.28
     another
    1.26
    Other
    1.25
     Others
    1.23
    Others
    1.19
    Act Density 0.078%

    No Known Activations