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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     puck
    -0.15
    vara
    -0.15
    openh
    -0.15
    hammer
    -0.15
    .mousePosition
    -0.15
    vik
    -0.14
    aments
    -0.14
    208
    -0.14
    ict
    -0.14
    afc
    -0.14
    POSITIVE LOGITS
    sted
    0.17
    aken
    0.17
    éru
    0.16
    ekim
    0.15
    olog
    0.15
    udden
    0.14
     positives
    0.14
    éĺ¶
    0.14
    pciones
    0.14
    .cl
    0.14
    Act Density 0.000%

    No Known Activations