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

    Neuronpedia

    INDEX
    Explanations

    connection words that enhance the flow of information in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    czy
    -0.20
    rib
    -0.14
     Architects
    -0.14
    _arch
    -0.14
     Byl
    -0.14
     Ire
    -0.13
    .tm
    -0.13
     åIJįåīį
    -0.13
     Called
    -0.13
    оÑı
    -0.13
    POSITIVE LOGITS
    eline
    0.16
     Verse
    0.14
    омеÑĢ
    0.14
     Wave
    0.14
    orte
    0.14
    interpret
    0.14
     Interpret
    0.14
     interpret
    0.14
    inke
    0.14
     Twitch
    0.13
    Act Density 0.000%

    No Known Activations