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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their placements in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.15
    .Microsoft
    -0.15
    .Addr
    -0.14
    YW
    -0.14
    dale
    -0.14
    óż
    -0.14
    peare
    -0.14
    ALE
    -0.14
    .slot
    -0.14
    머ëĭĪ
    -0.14
    POSITIVE LOGITS
    ĥĿ
    0.16
    haar
    0.15
     Dank
    0.15
    etsk
    0.14
     Mes
    0.14
     Silk
    0.14
    uxe
    0.14
    ipur
    0.14
    illac
    0.14
     Kramer
    0.14
    Act Density 0.086%

    No Known Activations