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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases that describe relationships or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     is
    -0.69
    pielen
    -0.56
     étages
    -0.53
     Juifs
    -0.53
     réguli
    -0.52
     témoins
    -0.52
     réfugiés
    -0.52
     está
    -0.51
    ificazione
    -0.50
     térm
    -0.49
    POSITIVE LOGITS
    ."</
    0.82
    posia
    0.79
     كومونز
    0.76
    ſelves
    0.75
     eventdata
    0.74
    )";
    0.74
     cherchés
    0.73
     '\\;'
    0.70
     */;
    0.69
     interactions
    0.67
    Act Density 0.556%

    No Known Activations