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

    Neuronpedia

    INDEX
    Explanations

    words indicating evaluation or judgment, particularly regarding communication and social expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .DEFINE
    -0.15
     Colbert
    -0.15
    azu
    -0.14
    emet
    -0.14
    alendar
    -0.14
     RUS
    -0.14
    zung
    -0.14
    าศ
    -0.14
    lesia
    -0.14
     SU
    -0.14
    POSITIVE LOGITS
     Mort
    0.32
    mort
    0.27
     mort
    0.26
    -mort
    0.25
     Mortgage
    0.25
    Tor
    0.24
     Tor
    0.24
     Stock
    0.21
     mortgage
    0.21
     Hed
    0.20
    Act Density 0.004%

    No Known Activations