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

    Neuronpedia

    INDEX
    Explanations

    topics related to analysis and methodology in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.78
     […]
    -0.74
    RegressionTest
    -0.71
    ОВО
    -0.70
     …
    -0.70
     ver
    -0.70
     Rees
    -0.69
     l
    -0.66
    НОЙ
    -0.66
    лло
    -0.65
    POSITIVE LOGITS
     ſind
    0.92
     houſe
    0.85
     ſtate
    0.79
    ]='\
    0.78
     Houſe
    0.78
     ſou
    0.77
     Diſ
    0.75
     faſt
    0.74
     ſmall
    0.73
     auffi
    0.73
    Act Density 0.028%

    No Known Activations