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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political parties and power struggles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbnails
    -0.81
    mentioned
    -0.80
     mentions
    -0.74
    cellaneous
    -0.71
     recalls
    -0.68
     mention
    -0.65
    nesday
    -0.65
     narration
    -0.64
     recalled
    -0.64
     Feast
    -0.64
    POSITIVE LOGITS
     indeed
    0.92
     truly
    0.88
     unacceptable
    0.77
     fundamentally
    0.76
     worthwhile
    0.75
    cellence
    0.75
     genuine
    0.74
     viable
    0.72
     sorely
    0.70
     capable
    0.70
    Act Density 0.933%

    No Known Activations