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

    Neuronpedia

    INDEX
    Explanations

    references to videos and calls to action to watch them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     written
    -0.47
     >
    -0.46
     ✅
    -0.45
    ostante
    -0.44
    ']>
    -0.44
    }';
    -0.44
    roquia
    -0.42
     pro
    -0.41
    лыша
    -0.41
    を書く
    -0.41
    POSITIVE LOGITS
     متعلقه
    0.89
     nahilalakip
    0.87
    expandindo
    0.81
    MethodManager
    0.79
     Normdatei
    0.78
     beginnetje
    0.74
     Wikispecies
    0.70
    Assista
    0.67
    InjectAttribute
    0.67
    Bronnen
    0.66
    Act Density 0.081%

    No Known Activations