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

    Neuronpedia

    INDEX
    Explanations

    references to documents and publications, particularly academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.81
    expandindo
    -0.81
    WebVitals
    -0.68
    saraba
    -0.67
    AnchorStyles
    -0.66
    GraphicsUnit
    -0.65
    PROLOG
    -0.61
     tartalomajánló
    -0.61
    ाहरण
    -0.57
     فريبيس
    -0.57
    POSITIVE LOGITS
     paper
    4.45
     Paper
    4.24
    Paper
    4.21
    paper
    4.15
     PAPER
    3.91
     papers
    3.55
    PAPER
    3.54
     Papers
    3.31
    papers
    3.05
    Papers
    3.01
    Act Density 0.070%

    No Known Activations