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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their affiliations or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    夫人
    -0.15
    quared
    -0.15
    -0.14
    pir
    -0.13
    âĢ¦↵↵
    -0.13
     oversh
    -0.12
     Col
    -0.12
     Cycle
    -0.12
    thro
    -0.12
    StringLength
    -0.12
    POSITIVE LOGITS
     reporting
    0.20
     reported
    0.18
    æĬ¥éģĵ
    0.17
     reporter
    0.17
    Reporting
    0.17
     Reported
    0.16
     Reporting
    0.16
     bureau
    0.16
     correspond
    0.16
     reporters
    0.15
    Act Density 0.118%

    No Known Activations