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

    Neuronpedia

    INDEX
    Explanations

    references to social media functionalities and user interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.38
    -0.35
    -0.34
    oneofs
    -0.33
    kit
    -0.32
    -0.32
    -0.31
    署
    -0.31
    srcs
    -0.31
    fly
    -0.31
    POSITIVE LOGITS
     si
    0.90
     se
    0.75
     kasarigan
    0.64
     je
    0.62
     się
    0.59
    WaitGroup
    0.59
    ="@+
    0.58
     sa
    0.54
    ConstraintMaker
    0.53
    awtextra
    0.51
    Act Density 0.205%

    No Known Activations