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

    Neuronpedia

    INDEX
    Explanations

    references to relationships or companionship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.10
    3:0.08
    4:0.07
    5:0.08
    6:0.08
    7:0.07
    8:0.08
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
     Peg
    -3.04
     Alpine
    -2.69
     Radio
    -2.56
     Prairie
    -2.54
     mole
    -2.53
     hosted
    -2.47
     Ai
    -2.46
     Frontier
    -2.46
     seaw
    -2.44
     Flores
    -2.43
    POSITIVE LOGITS
    afort
    3.20
    etsk
    3.08
    ourke
    2.82
    ilib
    2.75
     disadvant
    2.72
    Lenin
    2.68
    ettings
    2.67
    pmwiki
    2.66
    lopp
    2.66
    zsche
    2.66
    Act Density 0.000%

    No Known Activations