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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating various forms of support or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    едÑĮ
    -0.17
    anco
    -0.16
    unker
    -0.16
    akis
    -0.16
    å®Ļ
    -0.15
     Trit
    -0.15
    ikal
    -0.14
    ì·¨
    -0.14
     Opcode
    -0.14
    ":"/
    -0.14
    POSITIVE LOGITS
     himself
    0.17
    thane
    0.15
    ibaba
    0.14
    ube
    0.14
     chap
    0.14
     Aub
    0.14
    CSR
    0.14
     Drum
    0.14
    ole
    0.14
     Rooney
    0.14
    Act Density 0.210%

    No Known Activations