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

    Neuronpedia

    INDEX
    Explanations

    instances where documents discuss the act of reporting or addressing certain topics

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of covering various topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jet
    -0.77
    rian
    -0.73
     Sabha
    -0.72
    ellig
    -0.70
    lua
    -0.66
    rouse
    -0.65
    NG
    -0.65
    failed
    -0.64
    uni
    -0.63
    sett
    -0.63
    POSITIVE LOGITS
     covering
    0.90
     COVER
    0.85
     covers
    0.82
     cover
    0.81
    Cover
    0.81
    utical
    0.79
     Coverage
    0.79
    ages
    0.77
     wip
    0.76
    ength
    0.74
    Act Density 0.020%

    No Known Activations