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

    Neuronpedia

    INDEX
    Explanations

    symbols and special characters that signify importance or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    special characters, particularly a repeated symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.74
     dispers
    -0.72
     masse
    -0.72
     scattering
    -0.72
    nesday
    -0.68
    schild
    -0.68
    lda
    -0.68
    anwhile
    -0.66
     gad
    -0.66
     scatter
    -0.65
    POSITIVE LOGITS
    º
    1.07
    ®
    0.95
    ¹
    0.95
    į
    0.93
    £
    0.93
     âĢº
    0.90
    ı
    0.90
    Ī
    0.88
    ¬
    0.86
    ł
    0.84
    Act Density 0.106%

    No Known Activations