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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Ke" or its variations, suggesting a focus on names or titles starting with this sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    δη
    -0.18
    lic
    -0.15
     Forrest
    -0.14
    à¥ĩद
    -0.14
    adow
    -0.14
    asses
    -0.14
    åĽº
    -0.14
    link
    -0.14
    нÑı
    -0.13
    ncia
    -0.13
    POSITIVE LOGITS
    ystone
    0.27
    pler
    0.25
    plr
    0.22
    ystore
    0.22
     Karlov
    0.21
    plers
    0.21
    cil
    0.19
    Ke
    0.19
     Ke
    0.19
    ystate
    0.18
    Act Density 0.011%

    No Known Activations