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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments about individuals and their personalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ancor
    -0.16
    OK
    -0.15
    俺
    -0.14
     OK
    -0.14
     Realty
    -0.14
    EAR
    -0.13
     childs
    -0.13
    ãģķãĤī
    -0.13
     progn
    -0.13
     Schn
    -0.13
    POSITIVE LOGITS
    esson
    0.15
    enderit
    0.15
    hoa
    0.14
    è£ħç½®
    0.14
    langs
    0.14
     rn
    0.14
    aramel
    0.14
    .onView
    0.14
    жи
    0.14
    ieee
    0.14
    Act Density 0.143%

    No Known Activations