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

    Neuronpedia

    INDEX
    Explanations

    references to recognition and achievements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.08
    3:0.10
    4:0.33
    5:0.03
    6:0.05
    7:0.11
    8:0.03
    9:0.03
    10:0.08
    11:0.09
    Negative Logits
     EntityItem
    -1.69
    uesday
    -1.53
    apor
    -1.48
    ibling
    -1.47
    onge
    -1.47
    adi
    -1.46
    terday
    -1.45
    aten
    -1.41
     reacting
    -1.40
     greed
    -1.38
    POSITIVE LOGITS
     berth
    1.92
    �
    1.76
     Calder
    1.52
     accol
    1.51
     endorsements
    1.49
     invaluable
    1.45
     acclaim
    1.44
     Wilderness
    1.44
     nods
    1.44
     runtime
    1.43
    Act Density 0.029%

    No Known Activations