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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions related to engagement and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doméstica
    -0.51
     horaire
    -0.48
    руя
    -0.47
     choices
    -0.46
    gingen
    -0.46
    də
    -0.45
     offenbar
    -0.44
     Abp
    -0.44
    gment
    -0.44
     deserto
    -0.44
    POSITIVE LOGITS
     فريبيس
    0.82
    MemoryWarning
    0.81
    NameInMap
    0.71
     resourceCulture
    0.70
     stroll
    0.70
     betweenstory
    0.69
    сылкі
    0.68
    看一下
    0.68
     chuckle
    0.67
    Hochspringen
    0.67
    Act Density 0.219%

    No Known Activations