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

    Neuronpedia

    INDEX
    Explanations

    dialogue or conversational exchanges between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inate
    -0.18
    licit
    -0.17
    ilon
    -0.15
     tidy
    -0.15
     here
    -0.15
     Denn
    -0.14
     about
    -0.14
    Ļ
    -0.14
    ¹Ħ
    -0.14
     Silent
    -0.14
    POSITIVE LOGITS
     conspir
    0.16
    оки
    0.16
    icho
    0.15
    Å¡ov
    0.14
     tone
    0.14
    uale
    0.14
    ousse
    0.14
     voz
    0.14
     luder
    0.14
    Å¡e
    0.14
    Act Density 0.228%

    No Known Activations