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

    Neuronpedia

    INDEX
    Explanations

    patterns or references to alignment

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

    alignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HasKey
    -0.47
     McP
    -0.45
    newItem
    -0.45
    jMenuItem
    -0.45
    kloped
    -0.44
     Kela
    -0.44
    ket
    -0.43
    stdafx
    -0.42
    *************/
    -0.42
    Advertisement
    -0.41
    POSITIVE LOGITS
    Align
    2.56
     Align
    2.42
     align
    2.16
    align
    2.09
     ALIGN
    1.93
    ALIGN
    1.90
     aligning
    1.82
     aligns
    1.78
    Alignment
    1.77
     aligned
    1.62
    Act Density 0.008%

    No Known Activations