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

    Neuronpedia

    INDEX
    Explanations

    references to rivers and river-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paravant
    -0.81
     تضيفلها
    -0.76
    +#+
    -0.75
    躇
    -0.75
    MessageTagHelper
    -0.74
    aksana
    -0.70
    UIControlState
    -0.69
    mallows
    -0.69
     متعلقه
    -0.68
    phanie
    -0.68
    POSITIVE LOGITS
     rivers
    1.79
     River
    1.77
     river
    1.67
    River
    1.65
    Rivers
    1.62
     Rivers
    1.59
     Rivera
    1.55
     RIVER
    1.52
    rivers
    1.38
    river
    1.19
    Act Density 0.011%

    No Known Activations