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

    Neuronpedia

    INDEX
    Explanations

    entertainment-related terms or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yne
    -0.17
    pearance
    -0.15
    evi
    -0.15
    urette
    -0.15
    wner
    -0.15
    ottage
    -0.15
    売
    -0.14
    Ùijد
    -0.14
    IDX
    -0.14
    adow
    -0.14
    POSITIVE LOGITS
    ¯
    0.15
    utra
    0.14
    iku
    0.14
    uten
    0.14
     Kong
    0.14
     Norris
    0.14
    plates
    0.13
    icum
    0.13
    up
    0.13
     true
    0.13
    Act Density 0.000%

    No Known Activations