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

    Neuronpedia

    INDEX
    Explanations

    references to data structures and community-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intl
    -0.19
     Tet
    -0.17
     Rams
    -0.17
    resi
    -0.15
    ernote
    -0.15
    rrha
    -0.14
    acci
    -0.14
     Went
    -0.14
    _draft
    -0.14
    avigate
    -0.14
    POSITIVE LOGITS
    ÑĢай
    0.17
    sembl
    0.17
    ÑĪка
    0.16
    ì£Ħ
    0.15
     AW
    0.14
    bnb
    0.14
    onest
    0.14
    atical
    0.14
    interop
    0.13
    ffen
    0.13
    Act Density 0.000%

    No Known Activations