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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing approval or acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilee
    -0.17
    ilinx
    -0.17
    culus
    -0.15
    å·
    -0.15
    maal
    -0.15
    ile
    -0.15
    lot
    -0.14
     Kong
    -0.14
     tÃŃch
    -0.14
    ILE
    -0.14
    POSITIVE LOGITS
    454
    0.16
    égorie
    0.15
    .Navigator
    0.15
    Ñĥди
    0.15
    ably
    0.14
    asan
    0.14
    adle
    0.14
    ëĵĿ
    0.14
    geries
    0.14
    .spi
    0.14
    Act Density 0.051%

    No Known Activations