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

    Neuronpedia

    INDEX
    Explanations

    references to key messages or points being communicated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untas
    -0.19
    utin
    -0.17
     ÏĥÏĩ
    -0.15
    OLUMNS
    -0.14
    pector
    -0.14
    engin
    -0.14
    iddi
    -0.14
     thuáºŃn
    -0.14
    HING
    -0.14
    ITOR
    -0.14
    POSITIVE LOGITS
     loud
    0.34
     message
    0.32
    message
    0.28
     messages
    0.26
    -message
    0.25
    /message
    0.25
     Loud
    0.24
     Message
    0.24
    /messages
    0.23
    loud
    0.23
    Act Density 0.066%

    No Known Activations