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

    Neuronpedia

    INDEX
    Explanations

    references to ranking and performance indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rell
    -0.16
    ingham
    -0.15
    бол
    -0.15
    ãĥ©ãĥ¼
    -0.14
    gis
    -0.14
    ÙĪÙĦÙĬÙĪ
    -0.14
    adge
    -0.14
    olumn
    -0.14
    οÏħλ
    -0.14
    rouch
    -0.14
    POSITIVE LOGITS
    412
    0.15
    .hr
    0.14
     cr
    0.14
     lim
    0.14
    0.14
     acc
    0.14
     N
    0.13
    вед
    0.13
     AK
    0.13
     Cran
    0.13
    Act Density 0.005%

    No Known Activations