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

    Neuronpedia

    INDEX
    Explanations

    specific adjectives or phrases related to classification and status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.17
    roje
    -0.16
    .Contracts
    -0.16
    amerate
    -0.16
    aket
    -0.16
    293
    -0.16
    lse
    -0.16
    åĨĴ
    -0.15
     Robotics
    -0.14
    UBY
    -0.14
    POSITIVE LOGITS
    ella
    0.17
    gens
    0.16
    ëĤł
    0.15
     Holding
    0.15
    adaki
    0.14
    ãĥĬãĥ«
    0.14
    sg
    0.14
     Goose
    0.14
    SG
    0.14
     Colbert
    0.14
    Act Density 0.001%

    No Known Activations