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

    Neuronpedia

    INDEX
    Explanations

    phrases related to demands or calls for action

    oai_token-act-pair · gpt-3.5-turbo

    references to demands or calls for action from authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    milo
    -0.87
    ngth
    -0.77
    TED
    -0.76
    VERTISEMENT
    -0.75
    furt
    -0.75
    ategory
    -0.74
    ilon
    -0.73
    heit
    -0.72
    ahime
    -0.72
    figured
    -0.72
    POSITIVE LOGITS
     resignation
    1.07
     creation
    1.04
     cancellation
    1.02
     removal
    1.01
     feds
    1.00
     continuation
    0.99
     deletion
    0.99
     possibility
    0.97
     fullest
    0.96
     imposition
    0.95
    Act Density 0.180%

    No Known Activations