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

    Neuronpedia

    INDEX
    Explanations

    references to inspirational quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahn
    -0.15
    worthy
    -0.14
     --------------------------------------------------------------------------↵
    -0.14
    minster
    -0.14
     Prime
    -0.14
     Minh
    -0.13
    åİ
    -0.13
    ysqli
    -0.13
     legitimate
    -0.13
    ucc
    -0.13
    POSITIVE LOGITS
    obuf
    0.19
    inges
    0.19
    chal
    0.15
    alet
    0.15
    obus
    0.15
    illac
    0.15
    compress
    0.15
    大åħ¨
    0.15
    ksam
    0.15
    iddles
    0.15
    Act Density 0.031%

    No Known Activations