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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" with variations in intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayo
    -0.17
    abi
    -0.15
    ADVERTISEMENT
    -0.15
    EPROM
    -0.14
    advertisement
    -0.14
    ales
    -0.14
     ward
    -0.13
    tach
    -0.13
    istic
    -0.13
    awe
    -0.13
    POSITIVE LOGITS
    izik
    0.17
    Ī¬
    0.15
    /gif
    0.15
    ÑĨÑİ
    0.15
    ее
    0.14
    issan
    0.13
    Äįen
    0.13
    lava
    0.13
    umption
    0.13
    .argument
    0.13
    Act Density 0.162%

    No Known Activations