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

    Neuronpedia

    INDEX
    Explanations

    phrases that express comparisons or estimations using "as" and "percent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aidu
    -0.16
     esi
    -0.15
    asaki
    -0.15
    arlar
    -0.15
    ansi
    -0.14
    avenport
    -0.14
    alars
    -0.14
     modulation
    -0.14
    ŀæĢ§
    -0.14
     mod
    -0.14
    POSITIVE LOGITS
    .lazy
    0.15
    .clips
    0.15
    -dat
    0.15
    onga
    0.15
     Hole
    0.14
     ngừng
    0.14
    hil
    0.14
    CompleteListener
    0.14
    even
    0.14
    lerce
    0.14
    Act Density 0.113%

    No Known Activations