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

    Neuronpedia

    INDEX
    Explanations

    terms related to technological security and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health, medical conditions, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alike
    -0.55
    ,,,,
    -0.53
     assures
    -0.52
     meanwhile
    -0.48
    assetsadobe
    -0.46
     ensures
    -0.46
     Subtle
    -0.45
     tends
    -0.45
     tho
    -0.45
     immedi
    -0.44
    POSITIVE LOGITS
    ratom
    0.55
    oplan
    0.52
    gender
    0.44
    ãĤ¼
    0.42
    ouched
    0.41
    versive
    0.40
    hene
    0.40
    eteenth
    0.40
    miss
    0.40
    insert
    0.40
    Act Density 1.678%

    No Known Activations