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

    Neuronpedia

    INDEX
    Explanations

    capitalized text between quotes

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical sequences or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endeavour
    -0.80
     endeav
    -0.75
    boro
    -0.71
     Reincarnated
    -0.69
     regenerate
    -0.68
    arde
    -0.65
    ction
    -0.64
     allegiance
    -0.63
     footing
    -0.63
    utical
    -0.62
    POSITIVE LOGITS
    ³³³³³³³³
    1.04
    ³³³³
    1.04
    Newsletter
    1.00
    ³³³
    0.97
    ³³³³³³³³³³³³³³³³
    0.96
    Asked
    0.85
    Meanwhile
    0.83
    SPONSORED
    0.83
    Wisconsin
    0.83
    Article
    0.82
    Act Density 0.692%

    No Known Activations