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

    Neuronpedia

    INDEX
    Explanations

    phrases related to policy and politics

    oai_token-act-pair · gpt-3.5-turbo

    patterns of disagreement or contention in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abandon
    -0.71
    boro
    -0.68
     herself
    -0.63
     comple
    -0.63
     swall
    -0.62
    iki
    -0.61
     lifes
    -0.61
    odon
    -0.60
    fulness
    -0.59
     asleep
    -0.59
    POSITIVE LOGITS
    ccording
    0.90
    Until
    0.90
    Scroll
    0.89
    Unless
    0.87
    Ur
    0.85
    Unlike
    0.84
    Even
    0.84
    Indeed
    0.84
    âĢ¢âĢ¢
    0.83
    Asked
    0.82
    Act Density 0.593%

    No Known Activations