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

    Neuronpedia

    INDEX
    Explanations

    words related to practice and the act of performing skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anke
    -0.20
    aggi
    -0.18
    mans
    -0.17
    undan
    -0.16
    atta
    -0.15
    дина
    -0.15
    fax
    -0.15
    mand
    -0.15
    onden
    -0.14
    agi
    -0.14
    POSITIVE LOGITS
    itioner
    0.30
    ition
    0.29
    ising
    0.28
    ise
    0.25
    ised
    0.25
    icable
    0.23
    icum
    0.22
    iced
    0.22
    icing
    0.22
    ises
    0.21
    Act Density 0.004%

    No Known Activations