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

    Neuronpedia

    INDEX
    Explanations

    words related to close relationships or close connections

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "closely."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICAN
    -0.80
     Mania
    -0.71
    ————————
    -0.70
    IRO
    -0.70
    nos
    -0.69
    ule
    -0.69
    ulhu
    -0.69
    amaz
    -0.67
     Jackets
    -0.65
    ulia
    -0.65
    POSITIVE LOGITS
     aligned
    0.89
     cropped
    0.87
     resembles
    0.86
     enough
    0.84
     resemble
    0.82
     knit
    0.82
     minded
    0.81
     correlated
    0.80
     spaced
    0.80
    wired
    0.80
    Act Density 0.014%

    No Known Activations