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

    Neuronpedia

    INDEX
    Explanations

    syntax-related constructs in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zot
    -0.17
    inde
    -0.15
    kou
    -0.15
    cul
    -0.15
    enville
    -0.15
    arms
    -0.15
     Hammer
    -0.15
    íĥ
    -0.14
    QUOTE
    -0.14
    armor
    -0.14
    POSITIVE LOGITS
    èµ·
    0.15
     hei
    0.14
    isman
    0.14
    emple
    0.14
     çĦ
    0.14
     thick
    0.14
    873
    0.14
    orsi
    0.14
    oring
    0.14
    ÄĻd
    0.14
    Act Density 0.054%

    No Known Activations