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

    Neuronpedia

    INDEX
    Explanations

    phrases related to obtaining information or receiving answers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocal
    -0.16
    atest
    -0.14
    ano
    -0.14
    ži
    -0.14
    aka
    -0.14
    odash
    -0.14
    osti
    -0.13
     пÑĢиÑĤ
    -0.13
     Rica
    -0.13
    ait
    -0.13
    POSITIVE LOGITS
    chas
    0.20
    .ct
    0.16
     results
    0.15
     peace
    0.15
     access
    0.14
     rid
    0.14
    peace
    0.14
    idor
    0.14
    urdy
    0.14
    rise
    0.14
    Act Density 0.132%

    No Known Activations