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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ranking or popularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iferay
    -0.17
     Ãĸl
    -0.17
    crest
    -0.16
    à¹ĥà¸Ī
    -0.15
    psilon
    -0.15
    criptor
    -0.15
    pras
    -0.14
    hir
    -0.14
    ãģĵãģĿ
    -0.14
    Seconds
    -0.14
    POSITIVE LOGITS
    afa
    0.21
     searched
    0.20
     viewed
    0.19
    -view
    0.19
    -search
    0.19
     anticipated
    0.18
     followed
    0.18
     Val
    0.18
     Wanted
    0.18
     wanted
    0.17
    Act Density 0.025%

    No Known Activations