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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "continue" is used, suggesting operations or actions related to the continuation of a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AppModule
    -0.53
     MatDialog
    -0.52
    turn
    -0.52
     Adkins
    -0.51
    iomanip
    -0.51
    RepeatedField
    -0.49
     turn
    -0.49
    ComponentModel
    -0.48
    りゃ
    -0.47
    lus
    -0.47
    POSITIVE LOGITS
    +#+#
    0.86
     GenerationType
    0.86
     houſe
    0.84
    EndInit
    0.78
    BufferException
    0.77
    continue
    0.72
    IsContent
    0.70
     poffible
    0.70
    ExecuteReader
    0.70
     CURIAM
    0.70
    Act Density 0.018%

    No Known Activations