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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases that indicate the start of a discussion or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    posedge
    -0.42
    tanleria
    -0.39
    creativecommons
    -0.39
    Datuak
    -0.35
    InjectMocks
    -0.34
     roj
    -0.33
     Chriftian
    -0.33
    NavItem
    -0.33
    IGraphics
    -0.32
    clientX
    -0.32
    POSITIVE LOGITS
     surla
    0.72
     ***!
    0.65
    +#+#
    0.56
     zunächst
    0.54
    pierw
    0.54
    SBATCH
    0.54
    先是
    0.53
     terlebih
    0.52
     diikuti
    0.52
    OGND
    0.49
    Act Density 0.536%

    No Known Activations