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

    Neuronpedia

    INDEX
    Explanations

    terms related to application programming interfaces (APIs)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pile
    -0.18
    ikip
    -0.18
    li
    -0.17
    rees
    -0.17
    blind
    -0.17
    uer
    -0.16
    lah
    -0.16
    bed
    -0.16
    man
    -0.15
    mand
    -0.15
    POSITIVE LOGITS
    yonel
    0.19
    yah
    0.17
    ummings
    0.15
    ¤¤
    0.15
    atown
    0.15
    DOMNode
    0.14
     UClass
    0.14
    itized
    0.14
    .UIManager
    0.14
    datal
    0.14
    Act Density 0.010%

    No Known Activations