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

    Neuronpedia

    INDEX
    Explanations

    points or sections of a text that serve as structural markers or controls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -1.54
    GEBURTSDATUM
    -1.31
     resourceCulture
    -1.30
    Datuak
    -1.29
     CreateTagHelper
    -1.28
    Geplaatst
    -1.25
    mybatisplus
    -1.24
    HostException
    -1.22
    SBATCH
    -1.22
    RegressionTest
    -1.22
    POSITIVE LOGITS
    ↵↵
    1.21
    ↵↵↵
    1.01
    <h2>
    0.83
    ↵↵↵↵
    0.83
    1
    0.80
    <h3>
    0.79
    <b>
    0.79
    [toxicity=0]
    0.77
    ↵↵↵↵↵
    0.75
    <i>
    0.74
    Act Density 0.022%

    No Known Activations