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

    Neuronpedia

    INDEX
    Explanations

    specific names and terms associated with people, places, or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rou
    -0.17
    istrovstvÃŃ
    -0.16
    ower
    -0.15
    ãĤ
    -0.15
    ahoma
    -0.15
    κι
    -0.14
    plication
    -0.14
    gings
    -0.14
    ings
    -0.14
    ách
    -0.14
    POSITIVE LOGITS
    osate
    0.20
    zelf
    0.20
    xs
    0.18
    Ø©
    0.17
    ele
    0.17
    ะ
    0.17
    embre
    0.15
    zsche
    0.15
    zo
    0.15
    annis
    0.15
    Act Density 0.572%

    No Known Activations