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

    Neuronpedia

    INDEX
    Explanations

    mentions of data differences or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    delta and diff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cyfarwyddwr
    -0.35
    liesslich
    -0.33
    closeModal
    -0.32
     precepts
    -0.30
    pretation
    -0.29
    leroi
    -0.28
    andle
    -0.28
     Erziehung
    -0.28
    verton
    -0.28
    quement
    -0.28
    POSITIVE LOGITS
     Difference
    0.73
    difference
    0.71
     difference
    0.70
     Changes
    0.70
     differences
    0.70
     Differences
    0.69
    Diff
    0.68
    httphttps
    0.68
    Changes
    0.68
    Difference
    0.67
    Act Density 0.182%

    No Known Activations