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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating invitations or requests to participate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    invited to participate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bolí
    -0.39
    máscara
    -0.38
     ſtre
    -0.38
    expandindo
    -0.38
     stubborn
    -0.38
     carottes
    -0.37
     fallu
    -0.36
     Moscú
    -0.35
    savevideobot
    -0.35
    bookstore
    -0.34
    POSITIVE LOGITS
     invited
    1.60
     Invited
    1.55
    invited
    1.38
    Invited
    1.37
     invitado
    1.02
    vited
    1.01
     invitation
    0.96
     eingeladen
    0.89
     Invit
    0.86
     invite
    0.85
    Act Density 0.003%

    No Known Activations