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

    Neuronpedia

    INDEX
    Explanations

    references to historical events related to specific locations, particularly focused on tragic events like bombings

    oai_token-act-pair · gpt-3.5-turbo

    references to historical events and locations tied to significant tragedies, especially those involving Hiroshima

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cial
    -0.70
    Scot
    -0.69
    opoly
    -0.69
     bund
    -0.67
     rolls
    -0.66
    thal
    -0.66
     cod
    -0.65
    antine
    -0.64
     conduct
    -0.62
    aunder
    -0.62
    POSITIVE LOGITS
     Hiroshima
    3.05
    ampa
    1.47
     Ramirez
    1.39
    hp
    1.26
     plutonium
    1.26
    asaki
    1.17
     Hendricks
    1.16
     hp
    1.13
     horsepower
    1.07
    iem
    1.02
    Act Density 0.062%

    No Known Activations