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

    Neuronpedia

    INDEX
    Explanations

    significant numbers and punctuation in the context of interviews or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppers
    -0.15
    ej
    -0.15
     Webster
    -0.15
    kd
    -0.14
    tte
    -0.14
     leg
    -0.14
    ingu
    -0.13
     overhe
    -0.13
    sez
    -0.13
    islation
    -0.13
    POSITIVE LOGITS
    Q
    0.22
     Q
    0.20
     QUESTION
    0.17
    ilon
    0.16
    qed
    0.16
     Question
    0.16
    QDebug
    0.16
    ç»ĻæĪij
    0.15
    itsu
    0.15
    ariat
    0.15
    Act Density 0.135%

    No Known Activations