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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "know" in various contexts, highlighting uncertainty or self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __":
    -0.77
    __':
    -0.73
    __':
    -0.73
    __":
    -0.72
    참고
    -0.65
    ografija
    -0.64
     useCallback
    -0.63
    
    -0.58
    Datuak
    -0.58
    Morfologia
    -0.57
    POSITIVE LOGITS
    Busy
    0.51
     Busy
    0.51
     sabemos
    0.51
     banget
    0.50
     curtain
    0.48
     Allot
    0.47
    我知道
    0.46
     Garn
    0.46
     busy
    0.45
    InvalidProtocol
    0.44
    Act Density 0.173%

    No Known Activations