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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate historical timelines or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.83
     Meksiku
    -0.82
     Monfieur
    -0.78
     quæ
    -0.77
    UnusedPrivate
    -0.76
    ThroughAttribute
    -0.73
     ſtate
    -0.71
     ſeveral
    -0.70
     Majefty
    -0.69
     Diſ
    -0.68
    POSITIVE LOGITS
    ح
    0.57
     pretty
    0.49
     across
    0.45
     >::
    0.44
     greatly
    0.44
    scalatest
    0.43
    obium
    0.43
     from
    0.43
    WriteAttribute
    0.42
     omin
    0.42
    Act Density 0.344%

    No Known Activations