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

    Neuronpedia

    INDEX
    Explanations

    legal actions or formal procedures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ananas
    -1.28
     poire
    -1.27
     frambo
    -1.15
     trico
    -1.12
     marte
    -1.10
     persil
    -1.08
     tén
    -1.07
     fluo
    -1.05
     aquare
    -1.05
     strass
    -1.04
    POSITIVE LOGITS
     was
    0.90
     includes
    0.88
     came
    0.87
     went
    0.85
     consists
    0.82
     began
    0.82
     lasted
    0.81
     appeared
    0.79
     took
    0.79
     happened
    0.79
    Act Density 0.303%

    No Known Activations