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

    Neuronpedia

    INDEX
    Explanations

    references to shelters or places of protection and safety

    oai_token-act-pair · gpt-3.5-turbo

    terms related to shelters and places for refuge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.68
     tatt
    -0.65
     quizz
    -0.64
    lass
    -0.63
    phies
    -0.61
     resil
    -0.60
    ahon
    -0.60
     palp
    -0.59
     enqu
    -0.59
    orp
    -0.59
    POSITIVE LOGITS
     refuge
    0.88
    ãĥķãĤ¡
    0.81
    ctuary
    0.80
     shelter
    0.78
     Refuge
    0.77
    gence
    0.73
     Refugees
    0.73
    grounds
    0.72
    ously
    0.72
     shelters
    0.71
    Act Density 0.039%

    No Known Activations