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

    Neuronpedia

    INDEX
    Explanations

    terms related to guidance or instructional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forbes
    -0.76
    GEBURTSDATUM
    -0.75
     Kras
    -0.75
    texttt
    -0.70
    Morrison
    -0.70
     Vill
    -0.70
    },{
    -0.69
     DRAM
    -0.69
    beforeEach
    -0.69
     Eccl
    -0.68
    POSITIVE LOGITS
     guides
    1.78
     guide
    1.74
    guide
    1.68
     Guides
    1.67
    Guides
    1.65
    Guide
    1.63
     Guide
    1.63
     GUIDE
    1.56
     guid
    1.53
    guides
    1.51
    Act Density 0.086%

    No Known Activations