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

    Neuronpedia

    INDEX
    Explanations

    lyrically poetic language

    oai_token-act-pair · gpt-3.5-turbo

    adverbs ending in 'ly'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilater
    -0.78
     hemor
    -0.72
     respectively
    -0.70
    ĸļ
    -0.68
    ERA
    -0.66
     Annotations
    -0.66
     canvas
    -0.66
     ABE
    -0.66
     behavi
    -0.65
    senal
    -0.63
    POSITIVE LOGITS
    rics
    0.89
    lly
    0.88
    sis
    0.87
    upe
    0.85
    puff
    0.84
    ffe
    0.84
    pha
    0.83
    zed
    0.82
    tics
    0.81
    brate
    0.81
    Act Density 0.031%

    No Known Activations