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

    Neuronpedia

    INDEX
    Explanations

    references to specific cases or examples within discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.00
     виправивши
    -0.94
     itſelf
    -0.91
     ་་
    -0.85
     Houſe
    -0.85
     Shakspeare
    -0.84
     Diſ
    -0.84
     themſelves
    -0.83
    ſelves
    -0.83
     Majefty
    -0.82
    POSITIVE LOGITS
    :
    0.58
    如下
    0.57
     recent
    0.52
     notamment
    0.50
     particularly
    0.47
     proven
    0.47
    曖昧さ回避
    0.45
    Specifically
    0.44
     antaranya
    0.44
     esimer
    0.43
    Act Density 0.352%

    No Known Activations