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

    Neuronpedia

    INDEX
    Explanations

    comment syntax in programming languages, specifically related to documentation and annotations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -0.81
     fubject
    -0.81
     poffe
    -0.80
    Архівовано
    -0.78
     Jefus
    -0.76
     Majefty
    -0.74
    loài
    -0.74
     ejus
    -0.73
     Theſe
    -0.73
     poffible
    -0.71
    POSITIVE LOGITS
    AsUp
    0.65
    WithContext
    0.53
     за
    0.51
    vertreter
    0.51
    ingi
    0.49
    ciling
    0.49
    MIDDLEWARE
    0.48
     Idea
    0.48
    medio
    0.47
    TestBed
    0.47
    Act Density 0.004%

    No Known Activations