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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating initial impressions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esser
    -0.16
    ational
    -0.16
    ady
    -0.16
    oje
    -0.15
     جد
    -0.14
    绾
    -0.14
    PIP
    -0.14
    dub
    -0.14
    isky
    -0.14
    overe
    -0.14
    POSITIVE LOGITS
     glance
    0.49
     sight
    0.37
     quick
    0.30
    -gl
    0.29
     Sight
    0.29
     blush
    0.27
     look
    0.26
    quick
    0.26
     inspection
    0.26
     Gl
    0.25
    Act Density 0.028%

    No Known Activations