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

    Neuronpedia

    INDEX
    Explanations

    references to emotions and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.09
    2:0.21
    3:0.06
    4:0.02
    5:0.04
    6:0.04
    7:0.07
    8:0.05
    9:0.10
    10:0.08
    11:0.12
    Negative Logits
    buquerque
    -1.30
     Hitman
    -1.29
    olitical
    -1.28
    lance
    -1.27
    quartered
    -1.26
     vigilante
    -1.25
    emis
    -1.25
    earchers
    -1.23
    enary
    -1.23
    enth
    -1.23
    POSITIVE LOGITS
     MV
    1.63
    /)
    1.54
    Rh
    1.51
    /#
    1.44
     STL
    1.44
    CF
    1.43
    /,
    1.43
     LH
    1.36
    XL
    1.35
    nz
    1.34
    Act Density 0.003%

    No Known Activations