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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.18
    ickers
    -0.15
    ant
    -0.15
    OLS
    -0.15
    isk
    -0.15
    ÑĢабоÑĤ
    -0.15
     McGu
    -0.14
    isku
    -0.14
     thunk
    -0.14
    stu
    -0.14
    POSITIVE LOGITS
    otine
    0.16
    izi
    0.15
    dl
    0.15
    wiki
    0.14
    arch
    0.14
    plug
    0.14
    879
    0.14
    ARCH
    0.14
     otherwise
    0.13
     modern
    0.13
    Act Density 0.058%

    No Known Activations