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

    Neuronpedia

    INDEX
    Explanations

    the conjunction "but"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.73
    âĶĢâĶĢâĶĢâĶĢ
    -0.71
    seless
    -0.69
    MY
    -0.68
    utic
    -0.67
    QB
    -0.67
    pt
    -0.67
    à¨
    -0.66
    null
    -0.65
    ãĥİ
    -0.65
    POSITIVE LOGITS
     anecd
    1.36
     suffice
    1.14
     nevertheless
    1.09
     nonetheless
    1.07
     luckily
    0.93
     anecdotal
    0.90
     fortunately
    0.87
     hey
    0.86
     judging
    0.85
     indications
    0.82
    Act Density 0.188%

    No Known Activations