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

    Neuronpedia

    INDEX
    Explanations

    instances of non-verbal communication such as shrugging or chuckling

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    trump
    -0.77
    ãĤ·ãĥ£
    -0.74
    ãĥł
    -0.72
    TE
    -0.67
    jas
    -0.67
    FL
    -0.67
     Kardash
    -0.66
    establishment
    -0.65
    marked
    -0.65
    isi
    -0.65
    POSITIVE LOGITS
     nervously
    1.10
     bitterly
    1.07
     aloud
    1.04
     nostalg
    0.97
     scorn
    0.94
     sarcast
    0.94
     awkwardly
    0.92
     confidently
    0.90
     incred
    0.90
     loudly
    0.90
    Act Density 0.068%

    No Known Activations