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

    Neuronpedia

    INDEX
    Explanations

    references to source code or source files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tif
    -0.90
     <>",
    -0.81
     flocc
    -0.78
    ButterKnife
    -0.77
    aclk
    -0.75
    nastics
    -0.73
    Chim
    -0.69
    shadowRadius
    -0.69
    SBATCH
    -0.69
    Autoritní
    -0.69
    POSITIVE LOGITS
     SOURCE
    1.67
     source
    1.66
     Source
    1.56
     sources
    1.51
    Source
    1.46
    setSource
    1.40
    ource
    1.38
    source
    1.38
     Sources
    1.36
    sources
    1.30
    Act Density 0.064%

    No Known Activations