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

    Neuronpedia

    INDEX
    Explanations

    terms related to software reliability and voting systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasm
    -0.15
     Raz
    -0.15
    ROID
    -0.15
    redd
    -0.15
     McCart
    -0.14
     bon
    -0.14
    $rs
    -0.14
     Hindered
    -0.14
    gon
    -0.14
     Decomp
    -0.14
    POSITIVE LOGITS
    æĭĽ
    0.20
     vulnerable
    0.19
     susceptibility
    0.18
     vulnerability
    0.18
     ì·¨
    0.17
     susceptible
    0.16
    -risk
    0.16
    uppe
    0.16
     æĭĽ
    0.15
    invitation
    0.15
    Act Density 0.065%

    No Known Activations