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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a sense of obligation or emphasis on certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wynosi
    -0.69
    dough
    -0.56
    Dough
    -0.55
     PMID
    -0.55
    userModel
    -0.55
    vaders
    -0.54
    AnchorStyles
    -0.53
    ]\\
    -0.53
    Ligações
    -0.52
    toare
    -0.51
    POSITIVE LOGITS
     course
    1.24
    følgelig
    1.17
    course
    1.12
    verständlich
    1.12
     COURSE
    1.07
     Course
    1.02
     Natürlich
    0.99
     natürlich
    0.99
    Course
    0.95
    ürlich
    0.93
    Act Density 0.096%

    No Known Activations