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

    Neuronpedia

    INDEX
    Explanations

    occurrences of initialization functions or methods in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McCar
    -0.86
    ToMany
    -0.74
    bukkit
    -0.71
     springfox
    -0.69
     שוליים
    -0.66
    ModelSerializer
    -0.65
    lebo
    -0.65
    ETRIC
    -0.64
    ッケージ
    -0.62
    ומות
    -0.62
    POSITIVE LOGITS
    init
    1.63
    INIT
    1.60
     init
    1.59
     INIT
    1.50
    Init
    1.48
     Init
    1.46
     initState
    1.18
     初始化
    1.14
     Initializes
    1.13
    onInit
    1.11
    Act Density 0.045%

    No Known Activations