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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate invitations or welcoming messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uten
    -0.16
     Yong
    -0.15
    VERRIDE
    -0.15
    loor
    -0.15
    .Butter
    -0.14
     Reform
    -0.14
    æĦıæĢĿ
    -0.14
    elop
    -0.14
    iren
    -0.14
    iri
    -0.14
    POSITIVE LOGITS
     episode
    0.19
     part
    0.17
     edition
    0.17
    piar
    0.16
     era
    0.16
     Era
    0.16
    Welcome
    0.15
     another
    0.15
     my
    0.14
     Episode
    0.14
    Act Density 0.019%

    No Known Activations