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

    Neuronpedia

    INDEX
    Explanations

    actions related to conducting research and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Irrit
    -0.69
     Irrit
    -0.65
     ingrat
    -0.65
    Xna
    -0.64
    konomi
    -0.60
    بوابة
    -0.60
     offending
    -0.60
     Ressources
    -0.60
     bruised
    -0.59
     Alquiler
    -0.58
    POSITIVE LOGITS
    conducted
    1.14
     conducted
    1.10
    performed
    0.97
     effectué
    0.97
     performed
    0.94
    effectuer
    0.91
     undertake
    0.88
     perform
    0.87
     undertaken
    0.87
     extensive
    0.86
    Act Density 0.476%

    No Known Activations