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

    Neuronpedia

    INDEX
    Explanations

    references to specific years, events, and noted individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in the," indicating a focus on spatial or situational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rano
    -0.73
     therein
    -0.70
    MON
    -0.66
    igham
    -0.65
    IUM
    -0.65
    Continue
    -0.64
    SON
    -0.63
    inery
    -0.62
    Specific
    -0.62
    -)
    -0.61
    POSITIVE LOGITS
    roads
    0.93
    order
    0.90
    clus
    0.86
    clusively
    0.85
     order
    0.82
    humane
    0.78
     favor
    0.77
    sight
    0.77
     captivity
    0.77
    clusive
    0.76
    Act Density 0.055%

    No Known Activations