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

    Neuronpedia

    INDEX
    Explanations

    terms related to instruction or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.76
    Morrison
    -0.71
     Crum
    -0.66
    beforeEach
    -0.65
     Ellington
    -0.64
     Kras
    -0.64
    forbes
    -0.64
     Marlene
    -0.63
     Semantics
    -0.63
     Ellsworth
    -0.62
    POSITIVE LOGITS
     guide
    2.44
     guides
    2.39
    guide
    2.33
     Guide
    2.30
    Guide
    2.26
     Guides
    2.21
     GUIDE
    2.18
    Guides
    2.12
    guides
    2.01
    GUIDE
    1.98
    Act Density 0.042%

    No Known Activations