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

    Neuronpedia

    INDEX
    Explanations

    mentions of current US politics and related events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ende
    -0.74
     incorpor
    -0.72
     ponder
    -0.70
     imagination
    -0.66
     mushroom
    -0.65
     unwanted
    -0.64
     controvers
    -0.64
     salv
    -0.63
     jog
    -0.63
     pleasures
    -0.62
    POSITIVE LOGITS
    ï¸ı
    1.26
    ¯
    0.95
    ÃĽ
    0.92
    STEM
    0.91
    ï¸
    0.91
    cue
    0.86
    °
    0.85
    âĢł
    0.82
    said
    0.81
    âĻ¦
    0.81
    Act Density 1.478%

    No Known Activations