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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and functions presumably associated with API requests and response handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -1.16
     zwiſchen
    -1.06
     wiſſen
    -1.03
    <pad>
    -1.02
    <unused43>
    -1.02
    <unused14>
    -1.02
    <unused41>
    -1.02
    <unused28>
    -1.02
    <unused3>
    -1.02
    <unused8>
    -1.02
    POSITIVE LOGITS
     (
    1.64
    (
    1.56
    （
    0.95
    ($
    0.78
    ((
    0.78
    ("
    0.75
    }(
    0.74
    !(
    0.71
    ('
    0.68
     $(
    0.66
    Act Density 0.619%

    No Known Activations