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

    Neuronpedia

    INDEX
    Explanations

    topics related to safety and emergency preparedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stdc
    -0.42
    bcryptjs
    -0.35
    ftagPool
    -0.32
    addCriterion
    -0.31
     hasard
    -0.31
    balleur
    -0.30
     TRABAJO
    -0.29
    verifyException
    -0.29
     uLocal
    -0.29
     fakty
    -0.28
    POSITIVE LOGITS
     препратки
    0.69
    Datuak
    0.67
    <unused8>
    0.62
    <unused3>
    0.62
    <unused28>
    0.61
    <unused23>
    0.61
    <unused41>
    0.61
    <unused47>
    0.61
    [@BOS@]
    0.61
    <unused14>
    0.61
    Act Density 0.041%

    No Known Activations