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

    Neuronpedia

    INDEX
    Explanations

    rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.08
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.06
    7:0.07
    8:0.10
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     expans
    -3.00
    stal
    -2.95
     glob
    -2.75
    plet
    -2.70
    olit
    -2.61
     turnover
    -2.60
     purs
    -2.58
     youngest
    -2.58
     needy
    -2.57
     habit
    -2.56
    POSITIVE LOGITS
     Horses
    3.18
     Pearce
    3.18
    !".
    3.15
     Sturgeon
    3.14
     Hare
    3.08
     Miliband
    3.03
     Cheney
    3.00
     Fatal
    2.95
     Maiden
    2.94
     Cow
    2.90
    Act Density 0.000%

    No Known Activations