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

    Neuronpedia

    INDEX
    Explanations

    references to a specific name or brand, particularly in the context of success or achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rim
    -0.16
    sons
    -0.16
     Tarih
    -0.15
    شتر
    -0.15
    preter
    -0.15
    wij
    -0.15
    xeb
    -0.15
    à¹Ģย
    -0.15
    ombre
    -0.15
    ÑģÑĤÑĢо
    -0.14
    POSITIVE LOGITS
    pler
    0.25
    ating
    0.22
    ystone
    0.19
    egan
    0.19
    Ke
    0.19
     Karlov
    0.18
     Ke
    0.18
    ATING
    0.18
    plers
    0.17
    plr
    0.17
    Act Density 0.008%

    No Known Activations