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

    Neuronpedia

    INDEX
    Explanations

    recurring phrases that indicate additional content or continuation of a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.18
    stype
    -0.15
    pong
    -0.15
    MX
    -0.15
    /component
    -0.14
    ayo
    -0.14
    оÑĢÑĭ
    -0.14
     Qui
    -0.13
    ìĬµ
    -0.13
     Leban
    -0.13
    POSITIVE LOGITS
    brace
    0.16
    až
    0.15
    eker
    0.15
    izzo
    0.15
    ufs
    0.14
    /latest
    0.14
    oke
    0.14
    gon
    0.14
     Meet
    0.14
    ough
    0.14
    Act Density 0.012%

    No Known Activations