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

    Neuronpedia

    INDEX
    Explanations

    references to different countries

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rencies
    -0.83
    orsche
    -0.80
    sbm
    -0.72
    +=
    -0.71
    javascript
    -0.68
    uggest
    -0.67
    PsyNetMessage
    -0.66
    ocious
    -0.65
    sports
    -0.65
    aughs
    -0.65
    POSITIVE LOGITS
     vicinity
    0.98
     periphery
    0.96
     illegally
    0.94
     undet
    0.89
     treasury
    0.85
     confines
    0.83
     premises
    0.82
     itself
    0.82
     unlawfully
    0.80
     coffers
    0.77
    Act Density 0.501%

    No Known Activations