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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating growth or change in trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anning
    -0.17
    azen
    -0.16
    ilde
    -0.16
    ettel
    -0.15
    icable
    -0.15
    VICE
    -0.14
    EqualTo
    -0.14
    erb
    -0.14
    ulfilled
    -0.14
    onz
    -0.13
    POSITIVE LOGITS
     becoming
    0.30
     gaining
    0.23
    bec
    0.20
     Bec
    0.19
     one
    0.19
     seeing
    0.17
     among
    0.17
    ä¸Ģç§į
    0.17
     HOT
    0.17
     often
    0.16
    Act Density 0.285%

    No Known Activations