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

    Neuronpedia

    INDEX
    Explanations

    phrases related to staying or being in a particular location or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isz
    -0.18
    Äįas
    -0.17
    ild
    -0.16
     Wak
    -0.15
    olith
    -0.14
     Full
    -0.14
    egis
    -0.14
    imest
    -0.14
    riel
    -0.14
     Eins
    -0.14
    POSITIVE LOGITS
    å¼ĭ
    0.17
    ETCH
    0.16
    istra
    0.15
     overnight
    0.15
     pel
    0.15
     longer
    0.15
    ARGER
    0.15
    ble
    0.15
    ãģ£ãģį
    0.14
     Longer
    0.14
    Act Density 0.057%

    No Known Activations