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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly sequences of digits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.46
     ―――――
    -1.46
     itſelf
    -1.38
     themſelves
    -1.37
     pleaſure
    -1.35
     дописавши
    -1.34
     Anſ
    -1.33
     purpoſe
    -1.31
     snippetHide
    -1.31
     ſche
    -1.30
    POSITIVE LOGITS
     
    1.22
    x
    1.18
     x
    0.99
     G
    0.81
     S
    0.81
     C
    0.75
     B
    0.74
     L
    0.74
     Z
    0.74
     n
    0.73
    Act Density 0.174%

    No Known Activations