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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    the repeated conjunction "and" in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    activity
    -0.69
    uta
    -0.69
    uary
    -0.68
    Bas
    -0.67
    levant
    -0.67
    odcast
    -0.66
     Powered
    -0.66
    mit
    -0.65
    reference
    -0.65
    emi
    -0.65
    POSITIVE LOGITS
     furthermore
    1.10
     vice
    1.02
     secondly
    1.00
     THEN
    1.00
     therefore
    1.00
     consequently
    0.99
     moreover
    0.96
     then
    0.95
    romeda
    0.95
     hopefully
    0.92
    Act Density 0.279%

    No Known Activations