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

    Neuronpedia

    INDEX
    Explanations

    numbers related to technology or finance

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and figures related to financial or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morning
    -0.71
     Ot
    -0.71
     Land
    -0.69
     Wid
    -0.66
    hai
    -0.66
     Ll
    -0.64
    ware
    -0.63
     Carl
    -0.62
     bin
    -0.62
     Hol
    -0.62
    POSITIVE LOGITS
    265
    2.42
    264
    2.36
    267
    2.31
    285
    2.26
    263
    2.24
    270
    2.22
    287
    2.18
    277
    2.17
    268
    2.17
    269
    2.17
    Act Density 0.037%

    No Known Activations