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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographical locations, particularly mountains and bodies of water

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and natural landscapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cia
    -0.51
     Manual
    -0.48
     watchdog
    -0.47
     disclosures
    -0.47
     autobiography
    -0.46
     parole
    -0.46
    neau
    -0.46
     biography
    -0.46
    oyal
    -0.45
     Accountability
    -0.45
    POSITIVE LOGITS
     inhabited
    0.70
    near
    0.60
     lakes
    0.60
     encl
    0.59
    Temperature
    0.58
     lava
    0.57
    insula
    0.56
    conservancy
    0.56
     airst
    0.55
     Ruins
    0.55
    Act Density 1.564%

    No Known Activations