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

    Neuronpedia

    INDEX
    Explanations

    instances of specific foreign names or terms related to cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERGY
    -0.17
    nger
    -0.16
    arf
    -0.16
    alem
    -0.16
     longer
    -0.15
    ware
    -0.15
    ivable
    -0.15
    olut
    -0.14
     stom
    -0.14
    matic
    -0.14
    POSITIVE LOGITS
    uvre
    0.27
    iou
    0.27
    bling
    0.22
    hle
    0.19
    cker
    0.19
    olian
    0.18
    ufs
    0.17
    ae
    0.17
    oe
    0.17
    iš
    0.17
    Act Density 0.038%

    No Known Activations