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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experiences and feelings in a conversational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.67
     חיצוניים
    -0.56
     graag
    -0.55
     <=",
    -0.54
     téléphonique
    -0.53
    "]["
    -0.52
    änden
    -0.51
    ]].
    -0.51
     kaynağından
    -0.50
    ".
    -0.49
    POSITIVE LOGITS
    findpost
    0.55
     retenir
    0.51
    ########.
    0.50
    Doing
    0.50
     دیکھیے
    0.50
    oubliez
    0.49
    jarati
    0.47
     takeaway
    0.46
    ]),
    0.46
    SaveVideo
    0.46
    Act Density 0.124%

    No Known Activations