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

    Neuronpedia

    INDEX
    Explanations

    repeated references to a specific term or concept, particularly involving "atra."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Chop in citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.49
    RTLR
    -0.49
    gebraucht
    -0.48
    stuffed
    -0.48
    StoreMessageInfo
    -0.48
    Välislingid
    -0.46
    WEBPACK
    -0.45
    FieldError
    -0.45
    Buen
    -0.45
     насељу
    -0.45
    POSITIVE LOGITS
     Sinatra
    2.53
    atra
    1.69
     atra
    0.84
    Atra
    0.71
     Atra
    0.69
    atr
    0.62
    etra
    0.55
    attra
    0.52
     attraction
    0.52
    атра
    0.51
    Act Density 0.002%

    No Known Activations