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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing exclusivity or the concept of "not only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "not only"

    np_acts-logits-general · gemini-2.0-flash

    not only... but also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anche
    -0.71
     invece
    -0.59
     incluso
    -0.58
     even
    -0.56
    even
    -0.54
     nonetheless
    -0.53
     Even
    -0.52
    glBind
    -0.50
     même
    -0.49
     vraiment
    -0.49
    POSITIVE LOGITS
     myſelf
    1.24
     itſelf
    1.15
    ſelf
    1.13
     iſt
    1.09
    ſelves
    1.03
     estekak
    1.00
     pleaſure
    0.99
    RectangleBorder
    0.98
     ProtoMessage
    0.97
     becauſe
    0.94
    Act Density 0.083%

    No Known Activations