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

    Neuronpedia

    INDEX
    Explanations

    terms related to personal relationships and significant life aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.25
    1:0.03
    2:0.01
    3:0.05
    4:0.14
    5:0.06
    6:0.05
    7:0.13
    8:0.04
    9:0.06
    10:0.01
    11:0.10
    Negative Logits
     bandwagon
    -2.09
     ransomware
    -1.73
     lockdown
    -1.72
     Panic
    -1.69
     furiously
    -1.68
     Zac
    -1.66
     errone
    -1.66
     incorrectly
    -1.66
     prefix
    -1.64
    ovember
    -1.63
    POSITIVE LOGITS
     etc
    2.58
    ,...
    2.21
    estate
    2.08
     mates
    2.02
    .,
    2.00
    ,,,,
    2.00
     selves
    1.98
    selves
    1.97
    AppData
    1.94
    ankind
    1.90
    Act Density 0.006%

    No Known Activations