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

    Neuronpedia

    INDEX
    Explanations

    the word "shelter"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "shelter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gran
    -0.75
    cious
    -0.70
    lass
    -0.65
    sis
    -0.65
    Benz
    -0.63
    uncture
    -0.63
    uria
    -0.62
    visual
    -0.61
    nant
    -0.61
    cision
    -0.61
    POSITIVE LOGITS
     shelter
    1.30
     shelters
    1.14
     Shelter
    1.04
     refuge
    0.83
    ilitating
    0.81
     sanctuary
    0.79
     Refuge
    0.78
    ashtra
    0.74
    UFF
    0.73
    VILLE
    0.72
    Act Density 0.012%

    No Known Activations