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

    Neuronpedia

    INDEX
    Explanations

    devices related to technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to digital devices and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    origin
    -0.77
     Ambrose
    -0.75
     Alban
    -0.66
     oun
    -0.65
     Conclusion
    -0.63
    flags
    -0.61
     unions
    -0.59
    ¿½
    -0.59
    illard
    -0.59
     Avenger
    -0.58
    POSITIVE LOGITS
     screens
    0.84
    CHAT
    0.82
     glitch
    0.78
     screen
    0.72
    dating
    0.71
     glitches
    0.71
     ank
    0.71
     projector
    0.71
    printed
    0.70
     savvy
    0.70
    Act Density 0.474%

    No Known Activations