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

    Neuronpedia

    INDEX
    Explanations

    references to guides or guidance materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beforeEach
    -0.79
    texttt
    -0.76
    forbes
    -0.76
    Morrison
    -0.74
     Kras
    -0.73
    Personensuche
    -0.70
     Ellington
    -0.69
    Keefe
    -0.68
    machung
    -0.68
    GEBURTSDATUM
    -0.68
    POSITIVE LOGITS
     guides
    1.92
     guide
    1.89
    guide
    1.80
     Guides
    1.78
     Guide
    1.77
    Guide
    1.76
    Guides
    1.72
     GUIDE
    1.68
     guid
    1.58
    guides
    1.58
    Act Density 0.053%

    No Known Activations