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

    Neuronpedia

    INDEX
    Explanations

    references to "spin" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inine
    -0.17
    .ibatis
    -0.16
    ÙĬدÙĬ
    -0.15
    eness
    -0.15
    ilet
    -0.15
    afia
    -0.15
    quan
    -0.15
    ancock
    -0.15
    supply
    -0.14
    esini
    -0.14
    POSITIVE LOGITS
    ning
    0.28
    -spin
    0.25
     Spin
    0.23
    ners
    0.22
     Spinner
    0.20
     spin
    0.20
    Spin
    0.20
    NING
    0.20
    elli
    0.19
     spun
    0.18
    Act Density 0.008%

    No Known Activations