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

    Neuronpedia

    INDEX
    Explanations

    statements of procedures or guidelines in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orra
    -0.18
    uf
    -0.16
    edu
    -0.16
    oret
    -0.16
    eton
    -0.15
     instead
    -0.15
    utom
    -0.15
    cip
    -0.14
     while
    -0.14
    unker
    -0.14
    POSITIVE LOGITS
     always
    0.18
     ultimately
    0.17
     vždy
    0.16
    always
    0.16
     ALWAYS
    0.15
     ÙģØ¥ÙĨ
    0.15
    /Internal
    0.15
     Ultimately
    0.14
    137
    0.14
    706
    0.14
    Act Density 0.132%

    No Known Activations