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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating political hypocrisy and the avoidance of difficult discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subpo
    -0.16
    irie
    -0.13
    emony
    -0.13
    .dtd
    -0.13
    woord
    -0.13
    stÃŃ
    -0.13
    ůž
    -0.13
    iminal
    -0.13
    imeo
    -0.13
    _MAY
    -0.13
    POSITIVE LOGITS
     discussion
    0.96
     discussions
    0.81
    discussion
    0.77
     conversation
    0.75
     discuss
    0.75
     Discussion
    0.74
     debate
    0.73
     discussing
    0.69
    Discussion
    0.68
     discussed
    0.65
    Act Density 0.789%

    No Known Activations