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

    Neuronpedia

    INDEX
    Explanations

    specific names, likely related to prominent figures or contributors in a context such as film or sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.09
    3:0.07
    4:0.07
    5:0.10
    6:0.07
    7:0.09
    8:0.07
    9:0.09
    10:0.07
    11:0.09
    Negative Logits
    ichick
    -2.90
    Engineers
    -2.67
     wires
    -2.55
    zik
    -2.52
     sacks
    -2.52
     stupidity
    -2.49
     skulls
    -2.47
     screwed
    -2.45
    intel
    -2.42
    othy
    -2.41
    POSITIVE LOGITS
     Registration
    3.35
     FN
    3.03
     Festival
    2.95
     Hate
    2.93
     Aff
    2.89
     Royale
    2.75
     Regist
    2.63
     Origin
    2.62
     Fah
    2.62
     Gender
    2.61
    Act Density 0.000%

    No Known Activations