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

    Neuronpedia

    INDEX
    Explanations

    references to geographical or architectural features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.15
     صÙĨع
    -0.15
    tek
    -0.15
    eworld
    -0.15
    pNet
    -0.15
     !***
    -0.14
    odos
    -0.14
    antan
    -0.14
    ÄĻż
    -0.14
    ãĥ¼ãĤ¯
    -0.14
    POSITIVE LOGITS
     roy
    0.19
     pie
    0.18
     com
    0.18
     Pie
    0.18
    Pie
    0.17
     noble
    0.17
     Francie
    0.17
     vic
    0.16
     nonce
    0.16
     roi
    0.16
    Act Density 0.012%

    No Known Activations