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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user feedback and improvement in design or functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åħ¶ä¸Ń
    -0.13
    manuel
    -0.13
    cstdio
    -0.13
    isky
    -0.13
    unter
    -0.13
    -initialized
    -0.13
     lately
    -0.13
    ãģ¾ãģļ
    -0.13
     vừa
    -0.12
    _exempt
    -0.12
    POSITIVE LOGITS
     future
    1.00
    future
    0.83
     subsequent
    0.70
     further
    0.64
     Future
    0.63
     later
    0.63
    Future
    0.62
     бÑĥдÑĥÑī
    0.57
     futuro
    0.57
    _future
    0.54
    Act Density 0.741%

    No Known Activations