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

    Neuronpedia

    INDEX
    Explanations

    references to taking actions or making decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rá
    -0.16
    ÄĽ
    -0.15
    ho
    -0.14
    713
    -0.14
    ould
    -0.14
     touched
    -0.14
    ted
    -0.14
    rait
    -0.14
    ajs
    -0.14
    pte
    -0.14
    POSITIVE LOGITS
    elage
    0.16
    ismet
    0.16
     ettir
    0.15
    yor
    0.15
    praak
    0.14
    oga
    0.14
     fila
    0.14
    orthand
    0.14
    Ø·ÙĨ
    0.14
     Rog
    0.14
    Act Density 0.094%

    No Known Activations