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

    Neuronpedia

    INDEX
    Explanations

    repeating sequences or patterns in numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.49
     myſelf
    -1.47
     дописавши
    -1.40
     themſelves
    -1.37
     itſelf
    -1.36
     Anſ
    -1.33
    ."</
    -1.31
    ----</
    -1.30
     defaultstate
    -1.30
     doubtnut
    -1.29
    POSITIVE LOGITS
     
    1.23
    x
    1.02
     x
    0.95
     C
    0.82
     X
    0.78
     "
    0.77
     S
    0.76
    X
    0.75
     G
    0.75
     Z
    0.74
    Act Density 0.179%

    No Known Activations