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

    Neuronpedia

    INDEX
    Explanations

    references to familiarity and well-known concepts or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.62
    ➟
    -0.59
     pinulongan
    -0.59
    ipeline
    -0.56
    WSGI
    -0.54
     endforeach
    -0.54
    QFont
    -0.54
    MLLoader
    -0.52
    UserScript
    -0.51
    AndEndTag
    -0.50
    POSITIVE LOGITS
     familiar
    0.61
     familiarize
    0.52
    familiar
    0.51
     acquainted
    0.47
    Bom
    0.47
    Exotic
    0.45
     Bom
    0.45
    Familiar
    0.45
     bombs
    0.44
     bombe
    0.44
    Act Density 1.722%

    No Known Activations