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

    Neuronpedia

    INDEX
    Explanations

    generic phrases representing importance or priority

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing priority or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anmar
    -0.82
    rams
    -0.81
    fell
    -0.79
    yth
    -0.77
    ijn
    -0.76
    uador
    -0.76
    neys
    -0.74
    isodes
    -0.74
    Lyn
    -0.74
     Cosponsors
    -0.73
    POSITIVE LOGITS
     foremost
    0.95
     responders
    0.75
     contributor
    0.68
     sticking
    0.68
     importance
    0.68
     concern
    0.67
     distinguishes
    0.67
     cared
    0.66
    tenance
    0.66
     addressed
    0.65
    Act Density 0.025%

    No Known Activations