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

    Neuronpedia

    INDEX
    Explanations

    specific structures, components, and characteristics of materials or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vlan
    -0.15
    ektiv
    -0.15
    ispers
    -0.15
    xbc
    -0.14
    udit
    -0.14
    andle
    -0.13
    apat
    -0.13
    iffer
    -0.13
     operating
    -0.13
     Hack
    -0.13
    POSITIVE LOGITS
     touch
    0.26
     bis
    0.24
     extends
    0.23
    -touch
    0.22
     curve
    0.22
    extend
    0.22
    Extend
    0.21
    touch
    0.21
     touching
    0.21
     extend
    0.21
    Act Density 0.210%

    No Known Activations