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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to amplification or increased capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.19
    ر
    -0.18
    rnd
    -0.17
    lsen
    -0.17
    lad
    -0.17
    RF
    -0.16
    rand
    -0.16
    ladu
    -0.15
    argas
    -0.15
    berman
    -0.15
    POSITIVE LOGITS
    aign
    0.18
    elier
    0.17
    amp
    0.17
    agne
    0.17
    shire
    0.17
    y
    0.17
    agna
    0.17
    ylon
    0.17
    stead
    0.17
    site
    0.17
    Act Density 0.035%

    No Known Activations