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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "assume" and its variations, often highlighting presumptive statements or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekl
    -0.17
    ey
    -0.17
    ka
    -0.16
     nett
    -0.15
    erson
    -0.15
    rea
    -0.14
    .fixture
    -0.14
    811
    -0.14
    лÑĮ
    -0.14
    hem
    -0.14
    POSITIVE LOGITS
    upert
    0.17
     assum
    0.15
     vital
    0.15
     Assumes
    0.14
    /assert
    0.14
    -Bold
    0.13
    made
    0.13
    sız
    0.13
    isex
    0.13
    conds
    0.13
    Act Density 0.043%

    No Known Activations