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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hospitality and welcoming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ched
    -0.17
    seed
    -0.17
    ammen
    -0.16
    zelf
    -0.15
    rt
    -0.15
    jaw
    -0.15
    elho
    -0.14
    ohn
    -0.14
    shape
    -0.14
    uelles
    -0.14
    POSITIVE LOGITS
     aboard
    0.26
     into
    0.21
    /welcome
    0.20
    -home
    0.20
     addition
    0.20
     mat
    0.20
     visitors
    0.19
     warmly
    0.18
     arms
    0.18
     guests
    0.17
    Act Density 0.055%

    No Known Activations