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

    Neuronpedia

    INDEX
    Explanations

    crypto-related terms and references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     territo
    -0.66
     saad
    -0.64
    parency
    -0.61
     naer
    -0.61
     maraming
    -0.61
     najbol
    -0.59
     loob
    -0.59
     pagkak
    -0.58
     maksi
    -0.58
     taas
    -0.57
    POSITIVE LOGITS
     P
    0.62
    P
    0.57
     getP
    0.53
     PS
    0.52
     p
    0.51
    p
    0.50
    getP
    0.49
     PI
    0.49
     PF
    0.48
    setP
    0.48
    Act Density 0.912%

    No Known Activations