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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ùĩ
    -0.18
    ushman
    -0.17
    usercontent
    -0.15
    sans
    -0.15
    -0.15
    ãģĤãĤĬ
    -0.14
    ity
    -0.14
    esktop
    -0.14
    ignet
    -0.14
     study
    -0.14
    POSITIVE LOGITS
    /th
    0.23
    zelf
    0.19
    ched
    0.18
     particular
    0.17
     same
    0.17
    chers
    0.16
    ching
    0.16
    yonel
    0.15
    -ÑĤо
    0.15
    ches
    0.15
    Act Density 0.114%

    No Known Activations