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

    Neuronpedia

    INDEX
    Explanations

    punctuation and its surrounding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awe
    -0.17
    ILLA
    -0.15
    oser
    -0.15
    pter
    -0.15
    726
    -0.15
    onga
    -0.14
    pedo
    -0.14
    133
    -0.14
    pluck
    -0.14
    lej
    -0.14
    POSITIVE LOGITS
     so
    0.19
    but
    0.17
     dus
    0.16
    ãģłãģĭãĤī
    0.15
    so
    0.15
    ï¼ĮæīĢ以
    0.15
    ovit
    0.15
    羣æĺ¯
    0.14
    BT
    0.14
    åIJ¦
    0.14
    Act Density 0.276%

    No Known Activations