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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to positive experiences and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.78
    kháu
    -0.63
     كومونز
    -0.62
    WithIOException
    -0.61
     समीक्षक
    -0.57
     oprot
    -0.57
     PARSER
    -0.56
     betweenstory
    -0.56
    IsMutable
    -0.56
    ]**
    -0.56
    POSITIVE LOGITS
    UnsafeEnabled
    0.66
     كورة
    0.65
     للغاية
    0.59
    atissimo
    0.55
     dolci
    0.54
     demais
    0.54
     aniversário
    0.54
    każ
    0.53
     gynhyrchwyd
    0.53
    SpringBoot
    0.52
    Act Density 0.253%

    No Known Activations