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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "twice" and variations of frequency expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    slaught
    -0.17
    .Cryptography
    -0.17
    king
    -0.17
    embr
    -0.16
    shal
    -0.15
    nesia
    -0.15
    abet
    -0.15
    atic
    -0.15
     tạm
    -0.15
    ventus
    -0.14
    POSITIVE LOGITS
     times
    0.30
    -times
    0.27
    fold
    0.22
    -fold
    0.22
     Times
    0.21
     consec
    0.20
    /th
    0.20
     TIMES
    0.19
     throughout
    0.19
    -over
    0.19
    Act Density 0.045%

    No Known Activations