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

    Neuronpedia

    INDEX
    Explanations

    references to specific news agencies or media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    念
    -0.14
     physical
    -0.14
    acon
    -0.14
     supporting
    -0.14
     Marino
    -0.13
    inged
    -0.13
    uesto
    -0.13
    jay
    -0.13
    ↵
    -0.13
     greens
    -0.13
    POSITIVE LOGITS
    swire
    0.33
     wire
    0.31
    agency
    0.29
     agency
    0.28
     ag
    0.27
     Agency
    0.26
    wire
    0.26
    Wire
    0.25
     wires
    0.25
     Ag
    0.24
    Act Density 0.025%

    No Known Activations