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

    Neuronpedia

    INDEX
    Explanations

    mentions of locations or settings related to home

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "home."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]=>
    -0.75
    haps
    -0.63
     Canaver
    -0.63
    umbs
    -0.63
    utical
    -0.63
    immers
    -0.62
    umper
    -0.62
    andum
    -0.61
    uality
    -0.59
    ãģĨ
    -0.58
    POSITIVE LOGITS
    wife
    0.87
    coming
    0.86
     turf
    0.81
     courtyard
    0.80
    mates
    0.80
     depot
    0.76
    mate
    0.76
    chool
    0.75
    ported
    0.73
    artment
    0.73
    Act Density 0.030%

    No Known Activations