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

    Neuronpedia

    INDEX
    Explanations

    words associated with capability and possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    The
    -0.46
    .
    -0.44
    ↵↵
    -0.40
    Also
    -0.38
     in
    -0.36
    #
    -0.36
    “
    -0.36
     
    -0.35
    ?
    -0.35
    ↵
    -0.34
    POSITIVE LOGITS
     مرئيه
    0.94
     estekak
    0.88
    StructEnd
    0.81
    IUrlHelper
    0.80
    ésultats
    0.79
     EconPapers
    0.78
     autorytatywna
    0.78
    PYX
    0.77
    protoimpl
    0.77
     témoig
    0.77
    Act Density 0.587%

    No Known Activations