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

    Neuronpedia

    INDEX
    Explanations

    references to the word "tap" and its variations, indicating actions related to tapping or pressing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naco
    -0.65
     umat
    -0.56
    ERROR
    -0.56
    cinta
    -0.54
     grand
    -0.53
    袁
    -0.53
    bondale
    -0.53
    cutta
    -0.53
    meier
    -0.52
     Hoffman
    -0.52
    POSITIVE LOGITS
     taps
    2.45
     tap
    2.42
     Tap
    2.35
    Tap
    2.28
     tapped
    2.17
    taps
    2.11
    tap
    2.10
     tapping
    2.06
     TAP
    1.96
    TAP
    1.65
    Act Density 0.085%

    No Known Activations