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

    Neuronpedia

    INDEX
    Explanations

    the word 'mean' indicating statistical measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſmall
    -0.90
     Anſ
    -0.87
     neceffary
    -0.83
     poffible
    -0.82
     ſeveral
    -0.80
    ſelf
    -0.77
     ſever
    -0.76
     Houſe
    -0.74
    neſs
    -0.74
     reaſon
    -0.74
    POSITIVE LOGITS
     gates
    0.61
     mean
    0.58
     games
    0.57
     game
    0.54
    finals
    0.52
     JADX
    0.52
    JspWriter
    0.50
    holder
    0.48
     work
    0.48
     fun
    0.48
    Act Density 0.118%

    No Known Activations