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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating cause-and-effect relationships in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.91
     المعيارى
    -0.82
     الرياضيه
    -0.79
    TagMode
    -0.73
     pinulongan
    -0.69
    OGND
    -0.69
     queſta
    -0.69
    ðsíða
    -0.67
     témoig
    -0.66
    <unused43>
    -0.65
    POSITIVE LOGITS
    labelledby
    0.33
     notícia
    0.28
     Gutes
    0.27
     finally
    0.27
    GTCX
    0.26
    vét
    0.25
     alike
    0.25
     définitivement
    0.25
     Meksiko
    0.25
     berupa
    0.24
    Act Density 0.293%

    No Known Activations