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

    Neuronpedia

    INDEX
    Explanations

    references to measurement or quantity in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    th
    -0.17
    defgroup
    -0.15
    222
    -0.14
    rist
    -0.14
     approximately
    -0.14
    inder
    -0.14
     environ
    -0.14
     Reminder
    -0.13
    wik
    -0.13
    .blocks
    -0.13
    POSITIVE LOGITS
     decade
    0.23
     dozen
    0.21
     year
    0.19
     century
    0.19
     hour
    0.19
     month
    0.19
     hundred
    0.18
     thousand
    0.18
     acre
    0.17
    lettes
    0.16
    Act Density 0.027%

    No Known Activations