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

    Neuronpedia

    INDEX
    Explanations

    references to historical events, particularly wars and crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.53
     encomp
    -1.09
     intersper
    -1.07
     endow
    -0.89
     unve
    -0.89
    /***
    -0.87
     indestru
    -0.87
     underval
    -0.82
     quitted
    -0.81
    <?
    -0.80
    POSITIVE LOGITS
    CollectionUtils
    0.60
     Gnaden
    0.58
    gruntled
    0.57
    reportWebVitals
    0.57
    PhysRevLett
    0.57
    fillText
    0.55
     Tode
    0.55
     Herzen
    0.54
     caseros
    0.53
     ruinas
    0.53
    Act Density 0.603%

    No Known Activations