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

    Neuronpedia

    INDEX
    Explanations

    words indicating relationships or connections between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ald
    -0.15
    abwe
    -0.15
    ayo
    -0.14
    rin
    -0.14
     grass
    -0.14
    uve
    -0.13
    bose
    -0.13
    arse
    -0.13
    769
    -0.13
    uku
    -0.13
    POSITIVE LOGITS
     Baths
    0.15
    acre
    0.15
     Atmospheric
    0.14
    OLUMNS
    0.14
     INTERRUPTION
    0.13
    913
    0.13
    isle
    0.13
    TRS
    0.13
     chants
    0.13
    rame
    0.13
    Act Density 0.028%

    No Known Activations