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

    Neuronpedia

    INDEX
    Explanations

    locations and descriptive elements related to places

    oai_token-act-pair · gpt-3.5-turbo

    specific locations or structures related to buildings and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.68
    amiya
    -0.65
    izu
    -0.64
    ����
    -0.63
    Austral
    -0.62
    20439
    -0.61
    Posted
    -0.60
    Force
    -0.59
    Russell
    -0.59
    arov
    -0.58
    POSITIVE LOGITS
     itself
    0.88
    keeper
    0.88
    mate
    0.87
     emptied
    0.85
     layout
    0.82
     reopened
    0.79
    mates
    0.77
    wide
    0.77
    scape
    0.77
     overfl
    0.76
    Act Density 0.558%

    No Known Activations