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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases related to film and character development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukan
    -0.19
    ãĥªãĤ¢
    -0.15
    olf
    -0.15
     Erd
    -0.15
    onde
    -0.14
    ft
    -0.14
    Äįer
    -0.14
     proc
    -0.14
    uke
    -0.14
     poss
    -0.14
    POSITIVE LOGITS
    èo
    0.16
    ROTO
    0.16
    eled
    0.16
    λÏī
    0.16
    stroy
    0.15
    коÑĤ
    0.15
     Yayın
    0.14
    åIJĽ
    0.14
    ỹ
    0.14
    ault
    0.13
    Act Density 0.034%

    No Known Activations