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

    Neuronpedia

    INDEX
    Explanations

    references to time or specific moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.79
     MonoBehaviour
    -0.73
     Phry
    -0.72
     Huguen
    -0.72
     Josephus
    -0.68
     Silurian
    -0.65
     Tiberius
    -0.65
     Poincar
    -0.64
     Neop
    -0.64
     Mahomet
    -0.63
    POSITIVE LOGITS
     least
    1.37
     the
    1.00
    least
    0.90
    tests
    0.88
    Least
    0.87
    tempted
    0.87
    testing
    0.82
    tired
    0.80
     times
    0.76
     ease
    0.76
    Act Density 0.242%

    No Known Activations