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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advocating for a cause or position

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aredevil
    -0.73
    xtap
    -0.69
    rawler
    -0.67
     storing
    -0.66
    pping
    -0.64
    involved
    -0.61
     Ryder
    -0.61
    zed
    -0.61
    =~
    -0.60
     Soldiers
    -0.60
    POSITIVE LOGITS
     aloud
    0.96
     fluent
    0.94
    voice
    0.91
     louder
    0.88
     volumes
    0.86
     spoken
    0.85
     loudly
    0.81
     Mandarin
    0.80
     english
    0.77
     frankly
    0.73
    Act Density 0.384%

    No Known Activations