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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a specific condition or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe conditions or mechanisms related to governance and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cleanup
    -0.70
     surprised
    -0.65
     Reno
    -0.65
     professional
    -0.64
     scary
    -0.64
     busy
    -0.62
     context
    -0.61
     missing
    -0.61
     pros
    -0.60
     emb
    -0.60
    POSITIVE LOGITS
     wherein
    3.14
     whereby
    3.04
     comprising
    1.58
     namely
    1.37
     therein
    1.27
     herein
    1.25
     devised
    1.24
     comprises
    1.20
     secondly
    1.13
     thereof
    1.13
    Act Density 0.054%

    No Known Activations