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

    Neuronpedia

    INDEX
    Explanations

    announcements or reviews of software or technology updates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     defe
    -0.74
     disemb
    -0.74
     involuntary
    -0.72
     allowance
    -0.70
     separation
    -0.69
     dips
    -0.68
     enrol
    -0.67
     discipline
    -0.66
     manual
    -0.66
     assignment
    -0.65
    POSITIVE LOGITS
     Thankfully
    1.32
     Regardless
    1.21
     Additionally
    1.20
     Luckily
    1.20
     Needless
    1.19
     Fortunately
    1.17
     Unfortunately
    1.16
     Sadly
    1.13
     Nonetheless
    1.13
     Furthermore
    1.10
    Act Density 0.855%

    No Known Activations