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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is invited to an event or activity

    oai_token-act-pair · gpt-3.5-turbo

    words related to invitations and requests to attend events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rior
    -0.73
    grim
    -0.69
    rupted
    -0.68
    smart
    -0.63
    stead
    -0.63
    slave
    -0.62
    prototype
    -0.61
    ther
    -0.60
    bard
    -0.60
    gap
    -0.59
    POSITIVE LOGITS
     invitations
    1.23
     guests
    1.12
     invitation
    1.10
     invites
    0.89
     guest
    0.87
     invited
    0.85
     invite
    0.84
     inviting
    0.78
     bids
    0.78
     hither
    0.75
    Act Density 0.038%

    No Known Activations