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

    Neuronpedia

    INDEX
    Explanations

    phrases related to infrastructure and construction

    oai_token-act-pair · gpt-3.5-turbo

    references to infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.71
    CVE
    -0.70
    bed
    -0.70
     clay
    -0.64
    nery
    -0.61
    spring
    -0.60
    xit
    -0.60
    pole
    -0.59
    Buy
    -0.57
    castle
    -0.57
    POSITIVE LOGITS
    rast
    1.03
    inators
    0.98
    inating
    0.92
    inator
    0.87
    ination
    0.83
    ruct
    0.83
    ogle
    0.79
    aic
    0.78
    ulhu
    0.75
    minist
    0.75
    Act Density 0.016%

    No Known Activations