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

    Neuronpedia

    INDEX
    Explanations

    numerical values representing large areas of land

    oai_token-act-pair · gpt-3.5-turbo

    references to large areas of land measured in acres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     submar
    -0.74
     compulsion
    -0.71
     cumbers
    -0.69
     initiation
    -0.66
    uberty
    -0.65
    anwhile
    -0.65
    Doctors
    -0.65
     externalToEVAOnly
    -0.64
    âĹ¼
    -0.64
     imperson
    -0.63
    POSITIVE LOGITS
     acres
    1.20
     acre
    1.06
     farmland
    0.97
     hectares
    0.95
    rees
    0.93
     planted
    0.84
     apiece
    0.83
    acre
    0.79
    ģ«
    0.78
     woodland
    0.76
    Act Density 0.015%

    No Known Activations