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

    Neuronpedia

    INDEX
    Explanations

    words related to self, germ cells, or the reproductive system

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of self

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rabbit
    -0.74
     Valencia
    -0.70
     Decay
    -0.68
    Shot
    -0.65
     Flags
    -0.65
     Reign
    -0.61
     Powers
    -0.61
    ALS
    -0.61
     Canary
    -0.61
    FUL
    -0.61
    POSITIVE LOGITS
    actory
    1.17
    onso
    0.97
    entanyl
    0.96
    roth
    0.93
     bour
    0.91
    enn
    0.90
    oyd
    0.89
    ood
    0.89
    ayette
    0.86
    ranch
    0.86
    Act Density 0.009%

    No Known Activations