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

    Neuronpedia

    INDEX
    Explanations

    words related to the act of interpreting or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ey
    -0.19
    lund
    -0.19
    readcr
    -0.18
    aj
    -0.15
    uml
    -0.14
    fal
    -0.14
    erk
    -0.14
    drops
    -0.14
    quet
    -0.14
    etak
    -0.14
    POSITIVE LOGITS
    atively
    0.16
    .easy
    0.15
    hots
    0.15
     Pierce
    0.14
     Wade
    0.14
    окон
    0.14
    ntl
    0.14
    uka
    0.14
    мов
    0.14
    onz
    0.13
    Act Density 0.016%

    No Known Activations