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

    Neuronpedia

    INDEX
    Explanations

    key identifiers or references, particularly related to documentation or content display elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsche
    -0.17
     Bab
    -0.16
     EP
    -0.15
     Dra
    -0.14
     CPL
    -0.14
     Bed
    -0.14
     FP
    -0.14
    icensing
    -0.14
     AP
    -0.14
     AN
    -0.14
    POSITIVE LOGITS
    dG
    0.25
    bm
    0.25
    YW
    0.25
    Nm
    0.24
    YTE
    0.24
    cm
    0.23
    ZW
    0.23
    dm
    0.23
    cz
    0.23
    ZX
    0.23
    Act Density 0.001%

    No Known Activations