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

    Neuronpedia

    INDEX
    Explanations

    terms related to practice or training activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anke
    -0.20
    erland
    -0.17
    atta
    -0.17
    undan
    -0.17
    aucoup
    -0.15
    fax
    -0.15
    udeau
    -0.15
    undle
    -0.15
    mand
    -0.15
    osate
    -0.15
    POSITIVE LOGITS
    itioner
    0.36
    ICE
    0.33
    ition
    0.32
    ice
    0.32
    iced
    0.30
     ice
    0.28
    icing
    0.27
    ICES
    0.26
    ising
    0.24
     Ice
    0.23
    Act Density 0.004%

    No Known Activations