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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political campaigns and community response

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.87
    ESE
    -0.79
    uten
    -0.76
    Poké
    -0.75
    opsis
    -0.73
    OUND
    -0.72
    Connector
    -0.72
    ]).
    -0.69
    backer
    -0.68
    rations
    -0.68
    POSITIVE LOGITS
     admittedly
    0.94
     technically
    0.93
     occasionally
    0.88
     disagree
    0.85
     occasional
    0.84
     sometimes
    0.84
     laud
    0.81
     theoretically
    0.79
     faults
    0.78
     superf
    0.77
    Act Density 0.269%

    No Known Activations