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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and structures in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     command
    -0.14
     part
    -0.14
     element
    -0.14
    izr
    -0.13
    443
    -0.13
    赤
    -0.13
    eced
    -0.13
    overe
    -0.13
     bear
    -0.13
     cock
    -0.13
    POSITIVE LOGITS
    gree
    0.15
    isman
    0.15
    zie
    0.14
    agged
    0.14
    ầm
    0.14
    รร
    0.14
     Durant
    0.14
    heel
    0.14
    ÑģÑĥÑĤ
    0.14
    bserv
    0.13
    Act Density 0.184%

    No Known Activations