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

    Neuronpedia

    INDEX
    Explanations

    words related to foundational concepts or origins

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "root" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abwe
    -0.82
    psey
    -0.82
    eers
    -0.79
     disadvant
    -0.78
    vernment
    -0.77
    bilt
    -0.75
    urches
    -0.71
    chnology
    -0.71
    cffff
    -0.68
    eting
    -0.66
    POSITIVE LOGITS
    kit
    0.93
    beer
    0.90
     canal
    0.89
    stock
    0.87
     cellar
    0.87
     Canal
    0.87
    stocks
    0.84
    less
    0.76
    root
    0.75
    arious
    0.74
    Act Density 0.026%

    No Known Activations