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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igger
    -0.15
    ossa
    -0.15
     Piper
    -0.14
     Gio
    -0.14
    ose
    -0.14
    erves
    -0.14
    cee
    -0.14
    ative
    -0.13
    ãĥ³ãĥĢ
    -0.13
    legate
    -0.13
    POSITIVE LOGITS
     lead
    0.18
    lead
    0.16
    езÑĥлÑĮÑĤ
    0.15
     led
    0.15
     researcher
    0.15
    Lead
    0.14
    ILog
    0.14
    INY
    0.14
    research
    0.14
    ÑĮко
    0.14
    Act Density 0.082%

    No Known Activations