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

    Neuronpedia

    INDEX
    Explanations

    references to conversations or discussions on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anneer
    -0.16
    ura
    -0.15
    lemn
    -0.15
    ilia
    -0.15
    رÙĪز
    -0.14
    hlas
    -0.14
    uarios
    -0.14
     Nová
    -0.14
    otta
    -0.14
    achers
    -0.14
    POSITIVE LOGITS
    /dialog
    0.17
    -about
    0.16
    _about
    0.16
    ative
    0.16
    ırak
    0.16
     about
    0.15
     starter
    0.15
    about
    0.15
     between
    0.15
     starters
    0.15
    Act Density 0.056%

    No Known Activations