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

    Neuronpedia

    INDEX
    Explanations

    linguistic features related to reporting and commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sovere
    -0.14
    SystemService
    -0.13
    ataires
    -0.13
    ebek
    -0.12
    glich
    -0.12
    -Men
    -0.12
     Generation
    -0.12
    aż
    -0.11
    agens
    -0.11
    .amazonaws
    -0.11
    POSITIVE LOGITS
    isode
    0.18
    ultipart
    0.15
    quel
    0.15
    enade
    0.15
    logue
    0.14
    BaÅŁ
    0.14
    ogram
    0.14
    ifest
    0.14
    resher
    0.14
     Äijiá»ĥn
    0.13
    Act Density 0.375%

    No Known Activations