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

    Neuronpedia

    INDEX
    Explanations

    instances of invitations or invitations being extended to others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "invited" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urgy
    -0.68
    bard
    -0.65
    ther
    -0.63
     Rite
    -0.62
    avia
    -0.62
    tex
    -0.60
     Aerospace
    -0.60
    patch
    -0.59
    psc
    -0.58
     Bearing
    -0.58
    POSITIVE LOGITS
     invitations
    1.09
     guests
    1.07
     invitation
    0.93
     invite
    0.85
    unin
    0.81
     inviting
    0.80
     visitors
    0.80
     invites
    0.79
     attendees
    0.77
    #$
    0.73
    Act Density 0.015%

    No Known Activations