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

    Neuronpedia

    INDEX
    Explanations

    concepts related to actions, processes, and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leness
    -0.16
    .scalablytyped
    -0.16
     Astr
    -0.16
     Gardner
    -0.15
    usercontent
    -0.14
    ário
    -0.14
    ><![
    -0.14
    νÏĦ
    -0.14
     Anch
    -0.14
    ientes
    -0.14
    POSITIVE LOGITS
    ando
    0.33
    ating
    0.21
    ado
    0.21
    ar
    0.20
    ated
    0.18
    are
    0.18
    ador
    0.18
    641
    0.18
    ato
    0.17
    ada
    0.17
    Act Density 0.122%

    No Known Activations