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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inclusivity or addressing a wide audience

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people or collective entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOCK
    -0.60
    atts
    -0.58
    Initialized
    -0.57
    gio
    -0.56
    Blocks
    -0.55
    isu
    -0.55
    GET
    -0.54
     Majesty
    -0.54
    steen
    -0.54
    Invalid
    -0.53
    POSITIVE LOGITS
     thereof
    1.15
     associated
    1.12
     surrounding
    1.08
     related
    1.00
     attendant
    0.99
     accompanying
    0.95
     thereafter
    0.91
     ensuing
    0.90
     else
    0.90
     subsequent
    0.90
    Act Density 0.217%

    No Known Activations