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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and their relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -1.38
    LookAnd
    -1.31
    bootstrapcdn
    -1.13
     Мексичка
    -1.09
    httphttps
    -1.06
     transfieras
    -1.05
    DockStyle
    -1.03
    ConstraintMaker
    -1.00
    AddTagHelper
    -1.00
    </caption>
    -0.98
    POSITIVE LOGITS
    <eos>
    0.52
    h
    0.48
    in
    0.45
    ↵↵
    0.44
    т
    0.42
     the
    0.40
    ter
    0.40
     manos
    0.40
     specialized
    0.40
    ↵
    0.39
    Act Density 0.005%

    No Known Activations