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

    Neuronpedia

    INDEX
    Explanations

    acronyms or abbreviations related to organizations or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aret
    -0.17
    SID
    -0.16
    ró
    -0.16
    ameleon
    -0.16
    à¥įà¤ŀ
    -0.15
    NY
    -0.15
    NECT
    -0.15
    atar
    -0.15
    ny
    -0.15
    S
    -0.15
    POSITIVE LOGITS
    o
    0.19
    IU
    0.18
    ngine
    0.18
    psilon
    0.18
    agle
    0.17
    izabeth
    0.17
    oS
    0.16
    i
    0.15
    ster
    0.15
    corner
    0.15
    Act Density 0.069%

    No Known Activations