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

    Neuronpedia

    INDEX
    Explanations

    include statements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -1.15
     imagui
    -1.09
    <unused52>
    -1.02
    <unused79>
    -1.02
    <unused68>
    -1.02
    <unused16>
    -1.02
    <unused8>
    -1.02
    <unused14>
    -1.01
    <unused3>
    -1.01
    [@BOS@]
    -1.01
    POSITIVE LOGITS
    i
    0.49
    1
    0.49
    is
    0.49
    in
    0.47
    4
    0.46
    ’
    0.46
    3
    0.45
    e
    0.45
    0
    0.44
    I
    0.44
    Act Density 0.214%

    No Known Activations