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

    Neuronpedia

    INDEX
    Explanations

    numerical statistics and data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.16
    1:0.30
    2:0.03
    3:0.03
    4:0.03
    5:0.14
    6:0.03
    7:0.02
    8:0.06
    9:0.05
    10:0.06
    11:0.04
    Negative Logits
    Jimmy
    -1.94
    iate
    -1.84
    iced
    -1.80
    letal
    -1.76
    NL
    -1.75
    managed
    -1.74
    istor
    -1.74
    iated
    -1.73
    ��
    -1.70
    Compar
    -1.69
    POSITIVE LOGITS
     points
    2.74
     point
    2.08
     Points
    2.03
    point
    1.93
     rub
    1.89
    amina
    1.85
     franc
    1.79
     pts
    1.77
    points
    1.71
     Point
    1.70
    Act Density 0.003%

    No Known Activations