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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and related descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     equivalents
    -0.57
     notwithstanding
    -0.54
    entimes
    -0.54
    mmmm
    -0.53
    ograms
    -0.53
     positives
    -0.53
    illions
    -0.53
    @#
    -0.51
    ÃĥÃĤ
    -0.51
    avorite
    -0.50
    POSITIVE LOGITS
     Tehran
    0.67
     Bangkok
    0.64
     Islamabad
    0.63
     Borough
    0.62
     Belfast
    0.61
     Ankara
    0.61
     Melbourne
    0.61
     Beijing
    0.60
     Seoul
    0.60
     Shanghai
    0.59
    Act Density 0.930%

    No Known Activations