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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "form" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pai
    -0.17
    yy
    -0.15
    uti
    -0.14
     Gaul
    -0.14
    ary
    -0.14
    at
    -0.14
    rocket
    -0.14
    bé
    -0.14
    aty
    -0.14
    ette
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.18
    ulating
    0.17
    ulates
    0.17
    sWith
    0.16
    aklı
    0.15
     basis
    0.14
    urer
    0.14
    spender
    0.14
    ourcem
    0.14
    ossa
    0.14
    Act Density 0.031%

    No Known Activations