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

    Neuronpedia

    INDEX
    Explanations

    references to the word "sang" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imid
    -0.18
    wright
    -0.18
    096
    -0.15
    cház
    -0.15
    imus
    -0.14
    scratch
    -0.14
    abaj
    -0.14
    елен
    -0.14
    592
    -0.14
    angep
    -0.14
    POSITIVE LOGITS
    iov
    0.17
    spar
    0.17
    ster
    0.15
    &
    0.15
    ival
    0.15
     Thought
    0.15
    ria
    0.14
    pler
    0.14
    ertility
    0.14
    ones
    0.14
    Act Density 0.010%

    No Known Activations