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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific locations or entities, especially ones related to "Forest Hills."

    oai_token-act-pair · gpt-3.5-turbo

    references to forests and related geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esthetic
    -0.73
    demand
    -0.71
    verages
    -0.70
    soever
    -0.69
     observable
    -0.65
    DonaldTrump
    -0.65
    selves
    -0.64
    ifice
    -0.62
    atform
    -0.62
    interstitial
    -0.62
    POSITIVE LOGITS
     Forest
    1.03
    Forest
    0.93
    lands
    0.89
    land
    0.87
    lake
    0.87
     Lawn
    0.83
    ieri
    0.80
     Hills
    0.79
     Valley
    0.79
     Park
    0.78
    Act Density 0.007%

    No Known Activations