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

    Neuronpedia

    INDEX
    Explanations

    specific named entities or terms related to various industries and technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    P
    -0.38
    O
    -0.37
    ↵
    -0.37
    N
    -0.35
     P
    -0.35
    K
    -0.33
    M
    -0.33
    T
    -0.32
    A
    -0.32
    生
    -0.31
    POSITIVE LOGITS
    <unused79>
    1.23
    <unused52>
    1.23
    <unused8>
    1.22
    [@BOS@]
    1.22
    <unused14>
    1.22
    <unused16>
    1.22
    <unused23>
    1.22
    <unused28>
    1.22
    <unused3>
    1.21
    <unused41>
    1.21
    Act Density 0.430%

    No Known Activations