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

    Neuronpedia

    INDEX
    Explanations

    references to blogs and blogging-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lings
    -0.16
    urses
    -0.15
    inel
    -0.15
    <quote
    -0.15
    hend
    -0.14
    placer
    -0.14
    ezi
    -0.14
    ãĥ¼ãĤ¹
    -0.14
    eft
    -0.14
    edik
    -0.14
    POSITIVE LOGITS
    gers
    0.24
    arith
    0.24
    spot
    0.21
    osphere
    0.20
    ging
    0.19
    iversary
    0.18
    gin
    0.18
    gings
    0.17
    overn
    0.17
    gy
    0.16
    Act Density 0.019%

    No Known Activations