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

    Neuronpedia

    INDEX
    Explanations

    references to organizational structures and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pak
    -0.16
    abad
    -0.15
    atoi
    -0.15
    sut
    -0.15
    abi
    -0.15
    poke
    -0.14
    aes
    -0.14
    jit
    -0.14
    terior
    -0.14
    apat
    -0.14
    POSITIVE LOGITS
    eer
    0.14
     McCartney
    0.14
     spre
    0.13
     Perkins
    0.13
    dzi
    0.13
     Wa
    0.13
    stras
    0.12
    atura
    0.12
    .bc
    0.12
     Yan
    0.12
    Act Density 0.016%

    No Known Activations