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

    Neuronpedia

    INDEX
    Explanations

    terms related to electrical wiring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.63
    IndentedString
    -0.57
    čného
    -0.52
     &___
    -0.52
     révélé
    -0.51
     Wade
    -0.51
     {?>
    -0.50
     Classic
    -0.49
    čním
    -0.48
    GIVEREF
    -0.48
    POSITIVE LOGITS
     wire
    0.99
     wires
    0.89
     Wire
    0.86
    wires
    0.83
     WIRE
    0.76
    wire
    0.76
    Wire
    0.75
     Wires
    0.73
     wired
    0.72
     تانيه
    0.72
    Act Density 0.150%

    No Known Activations