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

    Neuronpedia

    INDEX
    Explanations

    repetitive patterns or consistency in relationships

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

    always same constant recurring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulemon
    -0.52
    ioutil
    -0.49
    賀状
    -0.46
     Compatibility
    -0.46
    loit
    -0.45
    nthetic
    -0.45
     Shine
    -0.45
    ouple
    -0.44
    amoto
    -0.44
    TacToe
    -0.44
    POSITIVE LOGITS
    UrlResolution
    0.50
     houſe
    0.48
     faſt
    0.46
     uſed
    0.45
     myſelf
    0.44
     recurring
    0.43
     ✭✭
    0.42
     siempre
    0.42
     pleaſure
    0.41
    ſelf
    0.39
    Act Density 0.107%

    No Known Activations