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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific research institute or possibly a name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kalk" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ples
    -0.82
    ODUCT
    -0.72
     CES
    -0.70
    ãģŁ
    -0.67
    GAME
    -0.66
    FTWARE
    -0.66
    isine
    -0.66
    verse
    -0.66
    cus
    -0.64
    ================================================================
    -0.64
    POSITIVE LOGITS
    enburg
    1.13
    owitz
    1.11
    iewicz
    1.02
    enstein
    1.01
    reath
    0.95
    rish
    0.89
    owski
    0.87
    alk
    0.86
    ulic
    0.84
    eneg
    0.82
    Act Density 0.033%

    No Known Activations