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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to guidance and direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.85
    forbes
    -0.72
    },{
    -0.71
    beforeEach
    -0.71
    ymce
    -0.69
    Personensuche
    -0.69
    situation
    -0.68
     Ellington
    -0.68
     Kras
    -0.67
    elsey
    -0.67
    POSITIVE LOGITS
     guide
    2.15
     guides
    2.08
     Guide
    2.02
    guide
    2.02
    Guide
    1.99
     Guides
    1.93
     GUIDE
    1.91
    Guides
    1.85
     guid
    1.77
    guides
    1.75
    Act Density 0.062%

    No Known Activations