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

    Neuronpedia

    INDEX
    Explanations

    the beginning of text segments or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     –
    -0.66
    ↵
    -0.65
     
    -0.65
     also
    -0.63
     but
    -0.63
             
    -0.61
     _
    -0.59
    </blockquote>
    -0.58
     fo
    -0.58
     so
    -0.58
    POSITIVE LOGITS
    webElementXpaths
    1.23
     unknownFields
    1.17
     itſelf
    1.14
    oredCriteria
    1.13
    expandindo
    1.12
    contentLoaded
    1.11
    DeleteBehavior
    1.11
    AccessorTable
    1.10
     myſelf
    1.10
     resourceCulture
    1.10
    Act Density 0.198%

    No Known Activations