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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references to scoring systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ot
    -0.17
     Cow
    -0.15
     vis
    -0.15
    uke
    -0.15
    ander
    -0.15
     Fav
    -0.15
     Naz
    -0.14
    zk
    -0.14
    959
    -0.14
     Minist
    -0.14
    POSITIVE LOGITS
    rál
    0.18
    .scalablytyped
    0.17
    ảo
    0.17
    ertino
    0.16
    LOSE
    0.16
    radu
    0.15
    endl
    0.15
    ê¼
    0.15
    ÄįÃŃ
    0.15
     tlak
    0.15
    Act Density 0.020%

    No Known Activations