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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences or reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.68
    Interess
    -0.60
    Interesting
    -0.57
     interest
    -0.56
    adə
    -0.55
    Decent
    -0.55
    jspb
    -0.54
     zainteres
    -0.54
    NOPQRST
    -0.54
     houſe
    -0.52
    POSITIVE LOGITS
     thank
    0.81
     couldn
    0.76
     THANK
    0.72
    couldn
    0.71
     treasure
    0.70
    THANK
    0.69
     thanking
    0.68
     Thank
    0.68
     truly
    0.65
     treasures
    0.65
    Act Density 0.169%

    No Known Activations