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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "own" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anter
    -0.16
    кÑĤа
    -0.15
    dar
    -0.15
    lei
    -0.15
     Conte
    -0.14
    enko
    -0.14
    .eof
    -0.14
    shal
    -0.14
    ivors
    -0.14
    coe
    -0.14
    POSITIVE LOGITS
    ienie
    0.14
    μι
    0.14
    ade
    0.14
     Pier
    0.14
    thon
    0.14
    ands
    0.14
    chaft
    0.13
    _managed
    0.13
     Keystone
    0.13
    jang
    0.13
    Act Density 0.012%

    No Known Activations