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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.20
    hana
    -0.20
    yar
    -0.20
    erin
    -0.20
    hud
    -0.19
    s
    -0.18
    ãģĦãĤĭ
    -0.18
    HASH
    -0.18
    sites
    -0.17
    ãģĦãģŁ
    -0.17
    POSITIVE LOGITS
    tes
    0.47
    ted
    0.45
    ters
    0.43
    ta
    0.42
    ting
    0.40
    tings
    0.38
    ten
    0.38
    ty
    0.36
    ts
    0.36
    ti
    0.33
    Act Density 0.085%

    No Known Activations