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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardi
    -0.21
     Lowell
    -0.18
    idel
    -0.17
    802
    -0.16
     Newport
    -0.16
    324
    -0.15
    ¢
    -0.15
     Stacy
    -0.15
    ssl
    -0.15
    59
    -0.15
    POSITIVE LOGITS
    73
    0.35
    72
    0.33
    173
    0.32
    172
    0.32
    174
    0.29
    71
    0.29
    74
    0.29
    073
    0.28
    175
    0.28
    171
    0.27
    Act Density 0.061%

    No Known Activations