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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate duration or ongoing developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ĵ
    -0.20
    Äįet
    -0.15
    ÅĤu
    -0.14
    esa
    -0.14
    arium
    -0.14
    	Copyright
    -0.14
    Updater
    -0.14
    rik
    -0.14
    izens
    -0.14
    dig
    -0.13
    POSITIVE LOGITS
     works
    0.46
     Works
    0.39
     pipeline
    0.36
    works
    0.35
    Works
    0.33
     Pipeline
    0.30
     making
    0.29
     pipelines
    0.29
    Pipeline
    0.27
     gest
    0.27
    Act Density 0.048%

    No Known Activations