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

    Neuronpedia

    INDEX
    Explanations

    references to sections, propositions, or subsections within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.16
    alach
    -0.14
    æĿ¡
    -0.14
    âng
    -0.14
    rej
    -0.13
    μιÏĥ
    -0.13
    Ģ
    -0.13
    zdy
    -0.13
    oli
    -0.13
    lane
    -0.13
    POSITIVE LOGITS
    atter
    0.14
    curring
    0.14
    ews
    0.13
    emain
    0.13
     material
    0.13
    osp
    0.13
     Cornwall
    0.13
     Jub
    0.13
     Rust
    0.13
     lift
    0.13
    Act Density 0.012%

    No Known Activations