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

    Neuronpedia

    INDEX
    Explanations

    words related to joy and positive emotions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.31
    public
    -0.75
    HasColumnType
    -0.69
    protected
    -0.65
    묶
    -0.64
    SequentialGroup
    -0.63
    marshaller
    -0.62
    /*
    -0.60
    /**
    -0.60
    private
    -0.60
    POSITIVE LOGITS
     jaya
    1.75
     wien
    1.66
     stockholm
    1.64
     Minang
    1.62
     bandung
    1.60
     thut
    1.59
     increa
    1.57
     aen
    1.57
     Juf
    1.56
     impra
    1.56
    Act Density 0.759%

    No Known Activations