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

    Neuronpedia

    INDEX
    Explanations

    references to empirical methods and experimental validation in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uin
    -0.14
    vell
    -0.14
    สม
    -0.14
     nou
    -0.14
    _caps
    -0.14
    _atts
    -0.14
     Pak
    -0.14
    izik
    -0.13
    hea
    -0.13
    quot
    -0.13
    POSITIVE LOGITS
     experiment
    0.36
     experimental
    0.29
     Experiment
    0.28
    experiment
    0.27
     experiments
    0.25
    Experiment
    0.24
    experimental
    0.24
     Experimental
    0.23
    Experimental
    0.22
    perimental
    0.21
    Act Density 0.029%

    No Known Activations