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

    Neuronpedia

    INDEX
    Explanations

    sports event descriptions or news updates

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that indicate specific formatting or notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scatter
    -0.78
     scattering
    -0.73
     pretext
    -0.67
     monop
    -0.66
     Patriot
    -0.65
     fragmentation
    -0.64
     seiz
    -0.64
     typew
    -0.63
     pace
    -0.63
    osate
    -0.63
    POSITIVE LOGITS
    §
    0.84
    atch
    0.82
    £
    0.82
    feat
    0.82
    elong
    0.82
    Fans
    0.80
    ĸļ
    0.80
    ¬
    0.79
    ¹
    0.78
    Hon
    0.77
    Act Density 0.598%

    No Known Activations