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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "Son" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tures
    -0.21
    resse
    -0.19
    ees
    -0.19
    eer
    -0.18
    een
    -0.17
    tings
    -0.17
    lett
    -0.17
    ture
    -0.16
    ément
    -0.15
    ozy
    -0.15
    POSITIVE LOGITS
    ny
    0.31
    orous
    0.28
    ntag
    0.26
    nen
    0.26
    nets
    0.24
    ething
    0.23
    net
    0.23
    der
    0.23
    oran
    0.22
    ship
    0.21
    Act Density 0.019%

    No Known Activations