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

    Neuronpedia

    INDEX
    Explanations

    references to financial or material resources

    oai_token-act-pair · gpt-3.5-turbo

    references to resources and their availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Topic
    -0.67
     mock
    -0.63
    Grad
    -0.62
    odo
    -0.62
    Spoiler
    -0.61
    cause
    -0.61
    dates
    -0.59
    effects
    -0.59
     theme
    -0.59
     Repe
    -0.59
    POSITIVE LOGITS
     allocated
    1.16
     allotted
    1.09
     amassed
    1.09
     available
    1.06
     expended
    1.03
     devoted
    1.02
     invested
    1.01
     reserves
    0.97
    available
    0.96
     capacity
    0.93
    Act Density 0.445%

    No Known Activations