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

    Neuronpedia

    INDEX
    Explanations

    phrases that express the complexities and challenges of the world

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elow
    -0.16
     Nationwide
    -0.15
    itel
    -0.15
    åħ¨åĽ½
    -0.14
    outil
    -0.14
    .FLAG
    -0.14
    ocz
    -0.14
     çŃ
    -0.14
    loff
    -0.14
    yc
    -0.14
    POSITIVE LOGITS
     ours
    0.21
     upside
    0.19
     unfair
    0.18
     vast
    0.18
     spinning
    0.18
     bigger
    0.17
     Hosp
    0.17
     smaller
    0.16
    éļª
    0.16
     indifferent
    0.16
    Act Density 0.173%

    No Known Activations