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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to belief, perception, and reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.88
     Efq
    -0.87
     Jefus
    -0.84
     Houſe
    -0.82
     itſelf
    -0.80
     houſe
    -0.77
    IntoConstraints
    -0.76
     ſtate
    -0.74
     ſeveral
    -0.74
     himſelf
    -0.73
    POSITIVE LOGITS
    SerializedSize
    0.50
    ReusableCell
    0.43
    解釈
    0.41
    JsonHelper
    0.41
     imagen
    0.41
    RegressionTest
    0.41
     tales
    0.41
     PARSER
    0.39
     betweenstory
    0.39
     Explanation
    0.38
    Act Density 0.081%

    No Known Activations