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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or entities associated with political, economic, and entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.10
    3:0.16
    4:0.32
    5:0.04
    6:0.03
    7:0.04
    8:0.02
    9:0.05
    10:0.08
    11:0.05
    Negative Logits
    iggurat
    -1.92
    proof
    -1.70
     =>
    -1.58
     simulated
    -1.57
    uted
    -1.56
    icester
    -1.54
    achable
    -1.48
    mir
    -1.48
    appropriate
    -1.46
    cooked
    -1.45
    POSITIVE LOGITS
     sake
    2.12
     purposes
    2.02
     coffers
    1.97
     aspiring
    1.87
     dearly
    1.83
    ankind
    1.79
     fledgling
    1.79
     newcomers
    1.79
    wat
    1.79
    $.
    1.77
    Act Density 0.280%

    No Known Activations