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

    Neuronpedia

    INDEX
    Explanations

    references to the word "tap" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    went
    -0.17
    ÑĢава
    -0.16
    edir
    -0.15
    LogLevel
    -0.15
    egg
    -0.15
    xae
    -0.15
    rema
    -0.15
    olation
    -0.15
    unner
    -0.15
    帯
    -0.15
    POSITIVE LOGITS
     tap
    0.27
     Tap
    0.23
    Tap
    0.22
     tapping
    0.21
    roots
    0.19
    into
    0.19
     taps
    0.19
    tap
    0.18
     tapped
    0.18
    enade
    0.18
    Act Density 0.012%

    No Known Activations