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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating durability and reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atar
    -0.17
     èĤ
    -0.15
    tbl
    -0.15
    ander
    -0.15
     Blanco
    -0.14
    760
    -0.14
    een
    -0.14
    REAK
    -0.14
     Barrett
    -0.14
    ÙĪاÙĨ
    -0.14
    POSITIVE LOGITS
     itself
    0.15
     withd
    0.15
    oÅĻ
    0.14
    reamble
    0.14
    zik
    0.14
    CodeAt
    0.14
    ceae
    0.14
    ople
    0.14
    .scalablytyped
    0.14
    PPER
    0.14
    Act Density 0.793%

    No Known Activations