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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating invitations or requests for participation

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

    "invite" or "invitation"

    np_acts-logits-general · gemini-2.0-flash

    invitations and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     døde
    -0.52
     dramatique
    -0.50
     financière
    -0.47
     arbejds
    -0.46
     stratégique
    -0.44
     mourut
    -0.44
    évalu
    -0.44
     fondament
    -0.44
     normaux
    -0.44
     avoient
    -0.44
    POSITIVE LOGITS
     invite
    1.41
     invitation
    1.40
     Invite
    1.30
     invited
    1.28
     invites
    1.27
     Invitation
    1.27
     inviting
    1.25
     invitations
    1.23
     invit
    1.18
    invite
    1.17
    Act Density 0.085%

    No Known Activations