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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures related to coding conventions or functions

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

    code containing if statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.12
     queſta
    -1.02
    <unused41>
    -0.91
    <unused74>
    -0.90
    <unused68>
    -0.90
    <unused52>
    -0.90
    <unused14>
    -0.90
    <unused16>
    -0.90
    <unused8>
    -0.90
    [@BOS@]
    -0.90
    POSITIVE LOGITS
     The
    0.49
    The
    0.49
    if
    0.48
     it
    0.45
     It
    0.43
     dolayı
    0.43
        
    0.42
     After
    0.42
     the
    0.42
     Using
    0.42
    Act Density 0.096%

    No Known Activations