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

    Neuronpedia

    INDEX
    Explanations

    words that indicate time or sequencing, especially those related to "after."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Externí
    -0.40
    openzeppelin
    -0.38
     Audiodateien
    -0.37
    MessageTagHelper
    -0.37
    DotNetBar
    -0.36
    ########.
    -0.35
     transfieras
    -0.34
    ️
    -0.34
     مرئيه
    -0.34
     <",
    -0.33
    POSITIVE LOGITS
    effects
    0.87
    effect
    0.84
    taste
    0.82
    thought
    0.82
    thoughts
    0.78
    glow
    0.76
    shock
    0.73
    wards
    0.73
    school
    0.67
     wards
    0.67
    Act Density 0.173%

    No Known Activations