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

    Neuronpedia

    INDEX
    Explanations

    terms related to drawing in or attracting various groups or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plode
    -0.17
    éĢļ
    -0.16
    ãĤĥ
    -0.15
    kili
    -0.15
    placeholders
    -0.15
    _render
    -0.14
     Karlov
    -0.14
    OpenHelper
    -0.14
    ALAR
    -0.14
    Received
    -0.14
    POSITIVE LOGITS
     attention
    0.33
    attention
    0.28
     talent
    0.26
    Attention
    0.24
     Attention
    0.24
     внимание
    0.23
     eyeb
    0.22
     interest
    0.22
    _attention
    0.20
     Talent
    0.20
    Act Density 0.072%

    No Known Activations