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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.77
    ſelves
    -0.77
     Jefus
    -0.77
     ſtate
    -0.77
     pleaſure
    -0.72
    ſelf
    -0.71
    PerformLayout
    -0.68
     bows
    -0.67
     Majefty
    -0.66
     purpoſe
    -0.66
    POSITIVE LOGITS
     IBOutlet
    0.67
    帖最后由
    0.66
     sodass
    0.60
     agar
    0.57
     supaya
    0.53
    zeitig
    0.49
     zodat
    0.49
     sắt
    0.47
     gela
    0.47
    arques
    0.47
    Act Density 0.149%

    No Known Activations