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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms, particularly in a technical or organizational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eron
    -0.20
    aliz
    -0.19
    eria
    -0.19
    al
    -0.19
    eri
    -0.18
    eca
    -0.18
    MR
    -0.18
    alis
    -0.18
    eres
    -0.17
    alink
    -0.17
    POSITIVE LOGITS
    olution
    0.31
    antage
    0.28
    oodoo
    0.23
    aporation
    0.23
    à¥įह
    0.22
    olved
    0.22
    IRONMENT
    0.22
    olumes
    0.21
    OLUTION
    0.21
    illage
    0.21
    Act Density 0.112%

    No Known Activations