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

    Neuronpedia

    INDEX
    Explanations

    references to specific films and their associated characters or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.47
    VolleyError
    -0.46
     wikipagina
    -0.44
    protetor
    -0.43
     Episcop
    -0.42
    发表于
    -0.42
     instanceof
    -0.42
    usercontent
    -0.41
    Geographie
    -0.39
    MutableLiveData
    -0.39
    POSITIVE LOGITS
     movie
    1.05
     film
    0.92
     movies
    0.84
    movie
    0.82
     Movie
    0.79
     filme
    0.79
     MOVIE
    0.78
    Movie
    0.77
     films
    0.76
     película
    0.73
    Act Density 0.517%

    No Known Activations