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

    Neuronpedia

    INDEX
    Explanations

    phrases related to non-traditional approaches or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arrera
    -0.16
    rss
    -0.15
    agn
    -0.14
     nhiên
    -0.14
    /reg
    -0.14
    815
    -0.14
    avery
    -0.14
    cue
    -0.14
    akit
    -0.13
     Tul
    -0.13
    POSITIVE LOGITS
     Con
    0.23
     convent
    0.23
    -tr
    0.22
    con
    0.21
     conv
    0.20
     conven
    0.19
    vention
    0.18
     convention
    0.17
    -con
    0.17
     rub
    0.17
    Act Density 0.027%

    No Known Activations