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

    Neuronpedia

    INDEX
    Explanations

    location names related to geopolitical events

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and their strategic significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.74
     Wonderland
    -0.65
    querque
    -0.62
    tumblr
    -0.59
    zona
    -0.57
     psychiat
    -0.56
    ADRA
    -0.56
    yright
    -0.56
    oola
    -0.55
     behold
    -0.54
    POSITIVE LOGITS
    pta
    0.61
    tsky
    0.61
    reshold
    0.60
    aternity
    0.56
     Tactics
    0.55
    utsche
    0.54
    hei
    0.53
     Pegasus
    0.53
    opers
    0.52
    pert
    0.51
    Act Density 0.633%

    No Known Activations