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

    Neuronpedia

    INDEX
    Explanations

    concepts and phrases related to simplicity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eenth
    -0.17
    asco
    -0.16
    esis
    -0.15
    402
    -0.15
    sel
    -0.15
    ngr
    -0.15
    rez
    -0.14
    lio
    -0.14
    ilities
    -0.13
    ulet
    -0.13
    POSITIVE LOGITS
    ton
    0.41
    tons
    0.40
    xes
    0.34
    TON
    0.29
    -minded
    0.29
    /simple
    0.28
     minded
    0.25
    ctic
    0.25
     straightforward
    0.25
    /basic
    0.24
    Act Density 0.037%

    No Known Activations