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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographical locations and travel destinations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.85
    =-=-=-=-
    -0.78
    apter
    -0.77
    osponsors
    -0.75
    Coin
    -0.74
    zos
    -0.71
    kos
    -0.70
    zees
    -0.70
    Phys
    -0.69
    intent
    -0.69
    POSITIVE LOGITS
     courtyard
    1.23
     surroundings
    1.19
     countryside
    1.19
     town
    1.15
     suburb
    1.14
     woodland
    1.11
     confines
    1.11
     rural
    1.11
     streets
    1.09
     valley
    1.09
    Act Density 0.174%

    No Known Activations