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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "similar" and its variations, indicating comparisons or likenesses between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izen
    -0.18
    å©
    -0.15
    vas
    -0.14
    alted
    -0.13
     Lambert
    -0.13
    ustos
    -0.13
    ìĦ¼
    -0.13
     intuition
    -0.13
    iven
    -0.13
    kul
    -0.13
    POSITIVE LOGITS
    pong
    0.16
    _utilities
    0.16
    YLON
    0.15
    à¤Ĥत
    0.14
     CHtml
    0.14
    ilters
    0.14
     Bender
    0.14
    è¼ī
    0.14
    нии
    0.14
     Swamp
    0.13
    Act Density 0.024%

    No Known Activations