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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and question-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    och
    -0.18
    enger
    -0.15
     competitive
    -0.14
     Sans
    -0.14
    aho
    -0.13
    ADVERTISEMENT
    -0.13
    ·
    -0.13
    vig
    -0.13
    raud
    -0.13
    ushman
    -0.13
    POSITIVE LOGITS
    Labels
    0.35
     Labels
    0.27
     tags
    0.24
     labels
    0.24
     Tags
    0.23
    âĨIJ
    0.23
    Tags
    0.22
    labels
    0.20
    tags
    0.20
    tag
    0.20
    Act Density 0.386%

    No Known Activations