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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and geographical descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hner
    -0.63
    cknow
    -0.60
     humanitarian
    -0.58
     emerged
    -0.57
    guyen
    -0.57
    odge
    -0.57
     culminated
    -0.56
     emerge
    -0.54
    ãĥ©ãĥ³
    -0.54
     emerges
    -0.54
    POSITIVE LOGITS
     anyways
    1.51
     haha
    1.38
     lol
    1.26
     anyway
    1.24
     :(
    1.20
     ;)
    1.10
     :)
    1.07
     whereas
    1.05
    !!!
    1.04
     ðŁĺ
    1.04
    Act Density 0.558%

    No Known Activations