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

    Neuronpedia

    INDEX
    Explanations

    terms related to investigative journalism and fact-checking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PCB
    -0.70
    interstitial
    -0.70
    mable
    -0.69
     goodbye
    -0.67
     STATES
    -0.66
     schematic
    -0.65
    oppable
    -0.65
     Prol
    -0.64
     Izan
    -0.63
     contiguous
    -0.63
    POSITIVE LOGITS
     journalism
    1.04
     Journalism
    0.90
     Reporting
    0.89
    ©¶æ
    0.83
    rina
    0.83
    athering
    0.80
    reporting
    0.80
     journalist
    0.79
    ument
    0.78
    icist
    0.77
    Act Density 0.628%

    No Known Activations