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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "start" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ores
    -0.16
    rint
    -0.15
    /Area
    -0.14
    aggio
    -0.14
    usu
    -0.14
    rides
    -0.14
    airs
    -0.14
    loating
    -0.14
    829
    -0.14
    ibrate
    -0.14
    POSITIVE LOGITS
    swith
    0.20
    tir
    0.16
    TM
    0.16
    ãģ°ãģĭãĤĬ
    0.15
    ecz
    0.15
    icho
    0.15
    _unregister
    0.14
    CLUDING
    0.14
    ovnÃŃ
    0.14
    PFN
    0.14
    Act Density 0.091%

    No Known Activations