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

    Neuronpedia

    INDEX
    Explanations

    references to months and numerical measurements of time or distance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arcer
    -0.18
    pedia
    -0.18
    lse
    -0.16
    ucht
    -0.14
    kke
    -0.14
    ãĤ¤ãĥī
    -0.14
    yla
    -0.14
    θο
    -0.14
    (PR
    -0.13
    peria
    -0.13
    POSITIVE LOGITS
    j
    0.15
    ans
    0.15
    ved
    0.15
    tit
    0.14
     MPU
    0.14
     Freund
    0.14
    umber
    0.14
    ana
    0.13
     NONINFRINGEMENT
    0.13
    emb
    0.13
    Act Density 0.003%

    No Known Activations