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

    Neuronpedia

    INDEX
    Explanations

    web links

    oai_token-act-pair · gpt-3.5-turbo

    references to additional information or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     marching
    -0.59
     targeted
    -0.58
     telecommunications
    -0.58
     constituency
    -0.57
     rallying
    -0.57
     sights
    -0.56
     broadcasting
    -0.55
     thrott
    -0.54
     aiming
    -0.54
     barg
    -0.54
    POSITIVE LOGITS
     Conclusion
    0.86
    Conclusion
    0.78
    ________________
    0.78
     Delete
    0.75
     CONTIN
    0.72
    ________________________________
    0.72
    EDIT
    0.72
    edit
    0.71
    APTER
    0.70
    VERTISEMENT
    0.70
    Act Density 0.523%

    No Known Activations