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

    Neuronpedia

    INDEX
    Explanations

    code-related structure definitions and logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Claw
    -0.19
    ©
    -0.17
    ¬
    -0.15
    rent
    -0.14
    £¼
    -0.14
     Gui
    -0.14
    ownt
    -0.14
     Bat
    -0.14
    ¬ģ
    -0.14
     RFC
    -0.13
    POSITIVE LOGITS
    vyk
    0.18
    Ī
    0.16
    orna
    0.16
    krv
    0.15
    chw
    0.15
    jvu
    0.15
    ÙĦÙĬÙĩ
    0.15
     thần
    0.15
    hawks
    0.14
    anax
    0.14
    Act Density 0.114%

    No Known Activations