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

    Neuronpedia

    INDEX
    Explanations

    HTML and JavaScript elements related to user interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML tags and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.84
     myſelf
    -0.82
    <unused41>
    -0.79
    <unused79>
    -0.79
    <unused16>
    -0.79
    <unused3>
    -0.79
    <unused14>
    -0.78
    <unused23>
    -0.78
    <unused8>
    -0.78
    <pad>
    -0.78
    POSITIVE LOGITS
     hid
    0.33
     waiting
    0.32
     ar
    0.31
     inf
    0.31
    i
    0.31
     
    0.30
     test
    0.28
    e
    0.28
    t
    0.28
     자
    0.28
    Act Density 0.048%

    No Known Activations