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

    Neuronpedia

    INDEX
    Explanations

    technical specifications related to filtering systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rig
    -0.18
    elson
    -0.18
    äºĮäºĮ
    -0.17
    out
    -0.15
    ri
    -0.15
    stad
    -0.15
    li
    -0.15
    	↵
    -0.14
    dal
    -0.14
    inand
    -0.14
    POSITIVE LOGITS
    nd
    0.30
    -thirds
    0.23
    nds
    0.17
    ampire
    0.17
    ifecycle
    0.17
    ndef
    0.16
    iterals
    0.16
    nda
    0.16
     thirds
    0.15
    adies
    0.15
    Act Density 0.272%

    No Known Activations