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

    Neuronpedia

    INDEX
    Explanations

    instances of expressions indicating anticipation or requests for attendance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untas
    -0.16
    irk
    -0.16
    enso
    -0.15
    rz
    -0.15
    ãģıãĤĵ
    -0.15
    adil
    -0.15
    або
    -0.15
    inker
    -0.14
    rzy
    -0.14
    alar
    -0.14
    POSITIVE LOGITS
    ãģĵãģ¡ãĤī
    0.21
     too
    0.20
     ÑĤоже
    0.20
     likewise
    0.19
     ebenfalls
    0.16
     particular
    0.15
     Lin
    0.14
     also
    0.14
     separately
    0.14
     similarly
    0.14
    Act Density 0.206%

    No Known Activations