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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific keywords related to events or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Royal
    -0.43
     P
    -0.41
     Pro
    -0.40
     pen
    -0.36
     C
    -0.36
     B
    -0.36
     R
    -0.36
     M
    -0.36
     p
    -0.36
     di
    -0.35
    POSITIVE LOGITS
    <unused23>
    1.14
    [@BOS@]
    1.13
    <unused17>
    1.13
    <unused42>
    1.13
    <unused43>
    1.13
    <pad>
    1.13
    <unused3>
    1.13
    <unused41>
    1.13
    <unused74>
    1.13
    <unused28>
    1.13
    Act Density 0.266%

    No Known Activations