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

    Neuronpedia

    INDEX
    Explanations

    phrases related to standing up and advocating for rights or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢап
    -0.15
    alez
    -0.15
    алеж
    -0.15
    eral
    -0.14
    263
    -0.14
    aight
    -0.14
     wors
    -0.13
     Aim
    -0.13
    605
    -0.13
    dre
    -0.13
    POSITIVE LOGITS
     stand
    0.38
     stood
    0.31
     stands
    0.30
     Stand
    0.28
     standing
    0.28
    Stand
    0.25
    _stand
    0.25
     assert
    0.24
    standing
    0.23
     voice
    0.23
    Act Density 0.324%

    No Known Activations