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

    Neuronpedia

    INDEX
    Explanations

    business-related terms, company names, and reports

    oai_token-act-pair · gpt-3.5-turbo

    various punctuation marks and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.90
    ctors
    -0.75
    omething
    -0.71
     scattering
    -0.68
    nown
    -0.66
    lda
    -0.65
     tremend
    -0.63
     caring
    -0.63
     scatter
    -0.62
    roots
    -0.62
    POSITIVE LOGITS
    º
    1.03
    ¹
    0.93
    ¬
    0.93
    ¡
    0.90
    Į
    0.87
    £
    0.86
    ł
    0.83
    į
    0.83
    âĢł
    0.82
    ı
    0.81
    Act Density 0.400%

    No Known Activations