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

    Neuronpedia

    INDEX
    Explanations

    bracket characters and their usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     U
    -0.60
    んですね
    -0.60
    くださいね
    -0.60
    phorbia
    -0.59
     amp
    -0.56
    brü
    -0.55
     O
    -0.54
    できました
    -0.53
    .
    -0.52
     cha
    -0.52
    POSITIVE LOGITS
    __(
    1.11
    (
    1.07
    >>(
    1.06
     gouttes
    1.03
     inoxydable
    1.03
    "]=
    1.00
    Revenir
    0.98
     goutte
    0.97
    ()(
    0.97
     larmes
    0.96
    Act Density 0.521%

    No Known Activations