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

    Neuronpedia

    INDEX
    Explanations

    the word "keep" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    marsh
    -0.17
    unas
    -0.17
    hood
    -0.16
    illery
    -0.16
    EXPORT
    -0.16
    ilib
    -0.14
    RET
    -0.14
    asin
    -0.14
    204
    -0.14
    prox
    -0.14
    POSITIVE LOGITS
     tabs
    0.24
    ake
    0.24
    _alive
    0.22
    alive
    0.21
    akes
    0.21
     pace
    0.21
    AKE
    0.20
     track
    0.20
     Tabs
    0.20
    Alive
    0.19
    Act Density 0.040%

    No Known Activations