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

    Neuronpedia

    INDEX
    Explanations

    ranges of numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yang
    -0.66
     axe
    -0.64
     hol
    -0.63
     axes
    -0.63
     scissors
    -0.62
     arrow
    -0.62
     pockets
    -0.61
     pill
    -0.60
    anski
    -0.60
    adesh
    -0.59
    POSITIVE LOGITS
    ãĤ¼ãĤ¦ãĤ¹
    0.96
    254
    0.87
     MPH
    0.85
    9999
    0.85
    999
    0.85
    230
    0.84
    266
    0.82
    degree
    0.81
    660
    0.81
    percent
    0.81
    Act Density 0.159%

    No Known Activations