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

    Neuronpedia

    INDEX
    Explanations

    references to safety standards and regulatory thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.15
    927
    -0.14
    -contrib
    -0.14
     bergen
    -0.13
    kos
    -0.13
    zac
    -0.13
    burg
    -0.13
    afari
    -0.13
     Weg
    -0.13
    LBL
    -0.13
    POSITIVE LOGITS
     threshold
    0.49
     thresholds
    0.46
    threshold
    0.45
     Threshold
    0.43
    Threshold
    0.38
    .threshold
    0.32
     thresh
    0.31
    éĺ
    0.28
    _threshold
    0.28
    _THRESHOLD
    0.25
    Act Density 0.193%

    No Known Activations