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

    Neuronpedia

    INDEX
    Explanations

    phrases describing a person's hellsih existence

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scattering
    -0.82
     scatter
    -0.75
     dispers
    -0.73
     confinement
    -0.71
     casting
    -0.70
     spinning
    -0.67
     staggered
    -0.67
     Bermuda
    -0.67
     shroud
    -0.67
     concentrating
    -0.66
    POSITIVE LOGITS
    ¹
    1.23
    º
    1.15
    £
    1.15
    į
    1.11
    Į
    1.11
    ¤
    1.08
    ĸļ
    1.07
    »
    1.05
    ®
    1.03
    ¡
    1.02
    Act Density 0.143%

    No Known Activations