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

    Neuronpedia

    INDEX
    Explanations

    concepts related to rules or standards governing behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Âĸ
    -0.15
    ·
    -0.15
     Moor
    -0.14
    adolu
    -0.14
    âĢIJ
    -0.14
    .appspot
    -0.14
    649
    -0.14
    lý
    -0.14
    =`
    -0.13
     CONST
    -0.13
    POSITIVE LOGITS
    0.48
    0.30
    0.29
     ??
    0.29
    0.25
    0.24
     ↵↵
    0.21
     âĢİ#
    0.18
     %%
    0.16
     âģ
    0.16
    Act Density 0.107%

    No Known Activations