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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to alignment or positioning

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

    alignment and its context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ''''
    -0.50
    ForeignKey
    -0.44
    3
    -0.44
    4
    -0.44
    HasKey
    -0.43
    0
    -0.43
     '':
    -0.43
     (−
    -0.41
    UObject
    -0.41
     ۱۳۸
    -0.41
    POSITIVE LOGITS
     ALIGN
    1.20
     Alignment
    1.15
     Align
    1.11
     alignment
    1.10
     aligning
    1.06
    Align
    1.05
     align
    1.04
    Alignment
    1.02
    ALIGN
    1.02
     alignments
    1.02
    Act Density 0.028%

    No Known Activations