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

    Neuronpedia

    INDEX
    Explanations

    negative phrases related to lack of answers and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _tolerance
    -0.17
    .rnn
    -0.14
    	xtype
    -0.14
    elder
    -0.14
    edd
    -0.14
    .ls
    -0.14
    PixelFormat
    -0.14
    á»ģn
    -0.14
    ORIZED
    -0.13
    NECT
    -0.13
    POSITIVE LOGITS
     YY
    0.26
     Y
    0.26
    (Y
    0.25
    /Y
    0.24
     CY
    0.24
    [Y
    0.23
    -Y
    0.23
    ,Y
    0.22
    YA
    0.21
    CY
    0.21
    Act Density 0.042%

    No Known Activations