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

    Neuronpedia

    INDEX
    Explanations

    words related to maintaining or preserving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minus
    -0.15
    ฤ
    -0.14
    237
    -0.14
    usterity
    -0.14
    itta
    -0.14
    *scale
    -0.14
    IRD
    -0.14
    ysl
    -0.14
    ieux
    -0.14
    ieu
    -0.14
    POSITIVE LOGITS
     tabs
    0.20
     alive
    0.19
    akes
    0.18
    _alive
    0.18
    alive
    0.17
     pace
    0.17
     costs
    0.17
     Tabs
    0.17
    à¹Ħว
    0.17
     things
    0.16
    Act Density 0.033%

    No Known Activations