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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and historical landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.16
    3:0.09
    4:0.24
    5:0.04
    6:0.06
    7:0.11
    8:0.04
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    seless
    -1.79
    oyal
    -1.53
     remorse
    -1.52
    ++)
    -1.49
     compliant
    -1.46
    inkle
    -1.45
     indisp
    -1.42
     impartial
    -1.39
     guilt
    -1.38
     dissenting
    -1.35
    POSITIVE LOGITS
    grab
    1.73
    cair
    1.69
    yip
    1.64
    ewater
    1.61
    atown
    1.56
     airst
    1.53
    ansas
    1.52
     Publishers
    1.52
    orks
    1.51
    erenn
    1.47
    Act Density 0.002%

    No Known Activations