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

    Neuronpedia

    INDEX
    Explanations

    mentions of teamwork and collaboration

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confiscated
    -0.71
     reported
    -0.68
     seized
    -0.67
     completed
    -0.66
     retrieved
    -0.66
     resumed
    -0.65
     duly
    -0.65
     promptly
    -0.65
     restored
    -0.64
     barred
    -0.64
    POSITIVE LOGITS
     yeah
    1.17
    laughs
    1.15
    Yeah
    1.08
     somebody
    1.05
    Whereas
    1.02
     secondly
    1.00
    you
    0.98
    Especially
    0.98
    Sometimes
    0.97
    entimes
    0.97
    Act Density 0.593%

    No Known Activations