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

    Neuronpedia

    INDEX
    Explanations

    references to experimental parameters and results in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esson
    -0.17
    ayload
    -0.14
    essen
    -0.14
    åŃĺäºİ
    -0.13
    oller
    -0.13
     today
    -0.12
    ogne
    -0.12
    UGIN
    -0.12
    /trunk
    -0.12
    oped
    -0.12
    POSITIVE LOGITS
     experiments
    0.36
     Experiment
    0.31
     experiment
    0.30
     experimental
    0.29
    å®ŀéªĮ
    0.28
     experimenting
    0.27
     Experimental
    0.27
    Experiment
    0.27
    periments
    0.26
    experiment
    0.26
    Act Density 0.107%

    No Known Activations