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

    Neuronpedia

    INDEX
    Explanations

    technical specifications related to electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cir
    -0.74
     Pepsi
    -0.68
     cler
    -0.68
     context
    -0.67
     sep
    -0.66
     Arabian
    -0.66
     Prometheus
    -0.65
     hiber
    -0.63
     Blizz
    -0.62
     bounce
    -0.62
    POSITIVE LOGITS
    mediated
    1.16
    derived
    1.09
    induced
    1.01
    MAG
    1.01
    PASS
    1.00
    sama
    1.00
    FM
    0.99
    sized
    0.98
    cert
    0.98
    based
    0.98
    Act Density 0.076%

    No Known Activations