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

    Neuronpedia

    INDEX
    Explanations

    invitation-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    rior
    -0.74
    rupted
    -0.71
    grim
    -0.69
    urgy
    -0.67
    smart
    -0.66
    roads
    -0.64
    ther
    -0.64
    ying
    -0.63
    bard
    -0.62
    slave
    -0.62
    POSITIVE LOGITS
     invitations
    1.21
     invitation
    1.14
     guests
    0.96
     invites
    0.88
     invite
    0.81
     inviting
    0.80
     invited
    0.80
     bids
    0.78
    eers
    0.77
     thereto
    0.76
    Act Density 0.025%

    No Known Activations