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

    Neuronpedia

    INDEX
    Explanations

    references to confidentiality and legal obligations surrounding personal information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    976
    -0.16
     Schl
    -0.14
    aks
    -0.14
     hö
    -0.14
     logic
    -0.14
     Tib
    -0.14
    емо
    -0.14
    âĶĶ
    -0.14
    owl
    -0.13
     bul
    -0.13
    POSITIVE LOGITS
    uras
    0.18
    -sensitive
    0.18
    aidu
    0.18
     sensitive
    0.17
     protect
    0.15
    à¤¾à¤Ł
    0.15
    Sensitive
    0.15
    ensitive
    0.15
    /stdc
    0.14
     protecting
    0.14
    Act Density 0.288%

    No Known Activations