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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of lists or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Madden
    -0.17
    tings
    -0.16
    irie
    -0.15
     adipisicing
    -0.14
    ména
    -0.14
     mue
    -0.14
    ónico
    -0.14
    zens
    -0.14
    าà¸ĩ
    -0.14
     Mines
    -0.14
    POSITIVE LOGITS
     among
    0.18
     Lunch
    0.17
    oot
    0.16
    among
    0.16
     Maj
    0.15
     amongst
    0.14
    .ObjectMeta
    0.14
     Among
    0.14
     pod
    0.14
    Among
    0.14
    Act Density 0.012%

    No Known Activations