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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or official documents

    oai_token-act-pair · gpt-3.5-turbo

    the word "of" and its associations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fights
    -0.77
    respective
    -0.75
    aciously
    -0.72
     polluted
    -0.71
     balcon
    -0.70
    rouse
    -0.69
     cyan
    -0.69
    anchez
    -0.68
     chops
    -0.68
     disse
    -0.67
    POSITIVE LOGITS
     Excellence
    1.19
     Names
    1.13
     Letters
    1.06
     Light
    1.05
     Accountability
    1.04
     Hours
    1.02
     Record
    1.02
     Lights
    1.02
     Hate
    1.01
     Balance
    1.01
    Act Density 0.126%

    No Known Activations