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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.23
    *
    -0.23
    i
    -0.22
    y
    -0.21
    ↵
    -0.21
    in
    -0.20
    h
    -0.20
    a
    -0.20
    t
    -0.20
    z
    -0.19
    POSITIVE LOGITS
    etc
    0.18
    ToSelector
    0.17
    UsageId
    0.17
    ,č↵
    0.17
    istrovstvÃŃ
    0.16
    izmet
    0.16
    Us
    0.15
    Orm
    0.15
    кÑĢа
    0.15
    Orange
    0.15
    Act Density 0.348%

    No Known Activations