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

    Neuronpedia

    INDEX
    Explanations

    references to the word "pop" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edly
    -0.20
    portlet
    -0.17
    eres
    -0.16
     slippery
    -0.14
    äm
    -0.14
    ÏĮγ
    -0.14
    ivor
    -0.14
    trinsic
    -0.14
    hoo
    -0.14
    .Drawing
    -0.14
    POSITIVE LOGITS
    /pop
    0.27
    ulating
    0.25
    ularity
    0.23
     Pop
    0.23
     pop
    0.23
    corn
    0.22
    -pop
    0.21
    Pop
    0.21
     popping
    0.20
    per
    0.19
    Act Density 0.021%

    No Known Activations