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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "without" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -1.18
     Monfieur
    -1.08
    ſelf
    -1.01
     Jefus
    -0.99
     houſe
    -0.97
     purpoſe
    -0.96
     Efq
    -0.90
     pleaſure
    -0.90
     ſhe
    -0.89
     ſche
    -0.88
    POSITIVE LOGITS
     Without
    1.58
     without
    1.54
    Without
    1.48
    without
    1.47
    Ohne
    1.40
    WITHOUT
    1.35
     WITHOUT
    1.34
     ohne
    1.26
     senza
    1.22
    Без
    1.10
    Act Density 0.081%

    No Known Activations