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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to percentages or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aney
    -0.17
    ãģĦãĤĭ
    -0.17
     Caldwell
    -0.16
    alus
    -0.16
    lane
    -0.16
    cheng
    -0.15
    dong
    -0.15
    ial
    -0.15
    ooke
    -0.14
    ade
    -0.14
    POSITIVE LOGITS
    ingly
    0.19
    housing
    0.16
    soever
    0.15
    æĤī
    0.15
    INUX
    0.15
    iness
    0.15
    uld
    0.15
     nghiá»ĩm
    0.14
    ites
    0.14
    orative
    0.14
    Act Density 0.147%

    No Known Activations