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

    Neuronpedia

    INDEX
    Explanations

    terms related to cars and automobiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     welcoming
    -0.56
     friendly
    -0.54
     nim
    -0.52
     hydraulic
    -0.52
     recep
    -0.52
     accepting
    -0.52
     spare
    -0.50
     prioriti
    -0.50
     independent
    -0.50
     collaborative
    -0.49
    POSITIVE LOGITS
     feroit
    0.77
     abstrato
    0.69
     enfans
    0.68
     auroit
    0.68
     zboží
    0.67
    httphttps
    0.67
     surla
    0.66
     Houſe
    0.65
     Infór
    0.65
     Kebijakan
    0.63
    Act Density 0.266%

    No Known Activations