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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the substring "Th" or words starting with "Th"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rana
    -0.15
    ugin
    -0.15
    ignment
    -0.15
     commission
    -0.14
    à¸IJ
    -0.14
     EÅŁ
    -0.14
     Commission
    -0.14
     commissions
    -0.14
    ession
    -0.13
    ateg
    -0.13
    POSITIVE LOGITS
    ompson
    0.23
    istle
    0.21
    oms
    0.20
    wait
    0.19
    iry
    0.19
    aimassage
    0.19
    iele
    0.19
    apa
    0.18
    .Tasks
    0.18
    orne
    0.18
    Act Density 0.009%

    No Known Activations