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

    Neuronpedia

    INDEX
    Explanations

    monetary values expressed in different currencies

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and their usage in numerical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     answ
    -0.73
    omorphic
    -0.66
    Ń·
    -0.63
     guiActiveUn
    -0.62
    Ļ½
    -0.61
    omorph
    -0.60
    £ı
    -0.59
    ãĥ¥
    -0.58
    (&
    -0.57
    tags
    -0.57
    POSITIVE LOGITS
     apiece
    0.68
    ²
    0.68
    eous
    0.66
    enic
    0.64
    ridges
    0.64
    yards
    0.63
     reserved
    0.62
    ãĥİ
    0.59
    aneous
    0.59
    }.
    0.59
    Act Density 0.084%

    No Known Activations