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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "admitted" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pac
    -0.17
    edo
    -0.16
     AssemblyCopyright
    -0.16
    omor
    -0.15
    atı
    -0.14
    ÙĦاÙĨ
    -0.14
    elsey
    -0.14
    åĭ
    -0.14
    ileceÄŁini
    -0.14
    /Admin
    -0.14
    POSITIVE LOGITS
     scales
    0.16
    andelier
    0.15
    istrar
    0.14
     dashes
    0.14
    istar
    0.14
     Tham
    0.14
    utsch
    0.14
     possession
    0.13
    etten
    0.13
     ongoing
    0.13
    Act Density 0.005%

    No Known Activations