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

    Neuronpedia

    INDEX
    Explanations

    concepts related to simplicity and minimalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rubber
    -0.16
    ModelProperty
    -0.14
     Safety
    -0.14
     Jad
    -0.14
    /movie
    -0.14
    alone
    -0.14
     safety
    -0.14
     Stellar
    -0.14
     rubber
    -0.14
     safely
    -0.14
    POSITIVE LOGITS
     simplicity
    0.19
    /simple
    0.18
     SIMPLE
    0.17
    ickerView
    0.16
     simples
    0.15
     simple
    0.15
    erule
    0.15
    simple
    0.15
    kker
    0.15
    ogui
    0.15
    Act Density 0.204%

    No Known Activations