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

    Neuronpedia

    INDEX
    Explanations

    locations or places within a city

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.78
     Dragonbound
    -0.73
    姫
    -0.71
    eering
    -0.69
     attent
    -0.68
    è¦
    -0.67
    éĹĺ
    -0.67
     Grizzlies
    -0.63
    eers
    -0.62
     externalToEVAOnly
    -0.62
    POSITIVE LOGITS
    ancing
    1.15
    arma
    1.11
    anced
    1.05
    uran
    1.05
    onest
    1.04
    ijk
    1.02
    arm
    1.00
    imm
    0.97
    orn
    0.95
    aval
    0.94
    Act Density 0.016%

    No Known Activations