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

    Neuronpedia

    INDEX
    Explanations

    words emphasizing the importance or necessity of concepts and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -fw
    -0.17
    ugg
    -0.15
    FAULT
    -0.14
    apus
    -0.14
    imson
    -0.14
     lav
    -0.14
    alted
    -0.14
    cult
    -0.14
    utta
    -0.14
     maybe
    -0.13
    POSITIVE LOGITS
     Lair
    0.15
    rschein
    0.15
    788
    0.14
    mdl
    0.14
    çŁ¥
    0.14
    quam
    0.14
    odore
    0.13
    ummer
    0.13
    erre
    0.13
    lio
    0.13
    Act Density 0.082%

    No Known Activations