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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "our" in various contexts, emphasizing collective ownership or concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.77
     they
    -0.62
     either
    -0.61
     my
    -0.58
    either
    -0.53
    enumi
    -0.52
     Either
    -0.50
     themselves
    -0.48
     itself
    -0.47
     vejo
    -0.47
    POSITIVE LOGITS
     ourselves
    0.87
    ſelves
    0.81
    selves
    0.79
     selves
    0.72
     dear
    0.71
     lives
    0.71
     hearts
    0.70
     planet
    0.67
    SEL
    0.67
     society
    0.66
    Act Density 0.189%

    No Known Activations