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

    Neuronpedia

    INDEX
    Explanations

    code snippets or syntax elements related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jedn
    -0.16
    rung
    -0.15
     Wyn
    -0.15
    óm
    -0.14
    .TYPE
    -0.14
    upo
    -0.14
     mej
    -0.14
    ãĥģãĥ¥
    -0.14
     dep
    -0.14
    виÑĩ
    -0.14
    POSITIVE LOGITS
    476
    0.16
    oden
    0.15
    037
    0.14
    --[
    0.14
    ensch
    0.14
    noinspection
    0.14
    InThe
    0.14
     Controls
    0.14
    137
    0.14
    benchmark
    0.13
    Act Density 0.015%

    No Known Activations