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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns 'you' and 'your' followed by verbs, often in questions, about opinions or recommendations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Lago
    -1.12
    ĸļ
    -0.98
    itized
    -0.96
     srfAttach
    -0.96
    ulic
    -0.96
     Presence
    -0.94
     Stats
    -0.92
    uces
    -0.91
    assembly
    -0.91
    edIn
    -0.90
    POSITIVE LOGITS
     think
    1.41
     intend
    1.40
     wish
    1.38
     guys
    1.36
     mean
    1.31
     reckon
    1.29
     know
    1.29
     want
    1.25
     feel
    1.21
     subscribe
    1.20
    Act Density 0.436%

    No Known Activations