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

    Neuronpedia

    INDEX
    Explanations

    references to the word "tap" and its variations, indicating a focus on tapping into something or extracting information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennent
    -0.15
    een
    -0.15
    sq
    -0.15
    edith
    -0.14
    er
    -0.14
    rema
    -0.14
    ivant
    -0.14
    /animate
    -0.14
    yang
    -0.14
    elpers
    -0.14
    POSITIVE LOGITS
     tap
    0.22
     Tap
    0.20
     tapping
    0.20
    Tap
    0.19
     tapped
    0.19
    asaki
    0.17
     brakes
    0.17
    VERN
    0.17
    azole
    0.17
     taps
    0.17
    Act Density 0.012%

    No Known Activations