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

    Neuronpedia

    INDEX
    Explanations

    conversational elements and interactions in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еви
    -0.15
    Aggregate
    -0.14
    âĢ¦âĢ¦ãĢĤ
    -0.14
     Wand
    -0.14
    à¸Ħ
    -0.14
    <Any
    -0.13
    adget
    -0.13
    Å¡Å¥
    -0.13
     наÑĢодÑĥ
    -0.13
    elsing
    -0.13
    POSITIVE LOGITS
     Um
    0.15
    nonnull
    0.15
     Bien
    0.15
     um
    0.15
    iza
    0.14
     exactly
    0.14
     excuse
    0.14
     absolutely
    0.13
    cae
    0.13
    tik
    0.13
    Act Density 0.064%

    No Known Activations