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

    Neuronpedia

    INDEX
    Explanations

    references to exclusive content or opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nings
    -0.16
    ings
    -0.16
    aving
    -0.16
    ether
    -0.15
    ani
    -0.15
    INGS
    -0.15
    ooks
    -0.15
    ched
    -0.15
    lsru
    -0.14
    /her
    -0.14
    POSITIVE LOGITS
    /un
    0.20
    ities
    0.18
    ively
    0.17
    -purpose
    0.17
    vely
    0.17
    idad
    0.16
    imports
    0.16
    /import
    0.15
    tl
    0.15
    人æīį
    0.15
    Act Density 0.030%

    No Known Activations