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

    Neuronpedia

    INDEX
    Explanations

    expressions of rarity and uniqueness in achievements or propositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    latin
    -0.15
    agan
    -0.15
    aug
    -0.14
    (TM
    -0.13
     Shape
    -0.13
    onda
    -0.13
    áb
    -0.13
    emain
    -0.13
    AB
    -0.13
    logfile
    -0.13
    POSITIVE LOGITS
    imeo
    0.16
    ifestyles
    0.16
    .scalablytyped
    0.15
    ider
    0.14
     Cotton
    0.14
    ìĹ¼
    0.14
     fitte
    0.14
    adin
    0.14
    .prot
    0.14
    ermo
    0.14
    Act Density 0.257%

    No Known Activations