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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.56
    Chham
    -0.55
    Diweddarwch
    -0.53
    Rüyada
    -0.50
    showthread
    -0.50
    shmi
    -0.49
    oplasty
    -0.49
    TextAppearance
    -0.48
    zków
    -0.48
     Lohan
    -0.47
    POSITIVE LOGITS
     Drapeau
    0.67
    <bos>
    0.62
    noons
    0.60
    MemoryWarning
    0.59
     hereto
    0.58
    ActionCreators
    0.58
    seamnă
    0.56
    delwed
    0.53
     estimés
    0.52
     affili
    0.51
    Act Density 0.436%

    No Known Activations