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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing intensity or emphasis, particularly surrounding the word "so."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Przypisy
    -0.52
    Tembelea
    -0.48
    WireFormatLite
    -0.45
     kasarigan
    -0.45
     חיצוניים
    -0.44
    urfs
    -0.44
    biggest
    -0.44
     op
    -0.43
    smallest
    -0.42
    Παραπομπές
    -0.42
    POSITIVE LOGITS
     mush
    0.88
     bit
    0.84
     much
    0.76
     muc
    0.76
    StoreMessageInfo
    0.75
     muck
    0.72
     deal
    0.71
     Muc
    0.68
     munch
    0.67
    uch
    0.66
    Act Density 0.129%

    No Known Activations