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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and physics

    oai_token-act-pair · gpt-3.5-turbo

    the presence of variations of the word "Neuron."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accounting
    -0.62
     referring
    -0.61
     allowances
    -0.59
     sidx
    -0.57
     injection
    -0.56
     stewards
    -0.56
    noon
    -0.56
     buzzing
    -0.55
     BaseType
    -0.55
     briefing
    -0.54
    POSITIVE LOGITS
    braska
    1.38
    arest
    1.33
    olithic
    1.29
    umann
    1.27
    utral
    1.26
    verend
    1.23
    oliberal
    1.19
    uron
    1.16
    arer
    1.12
    utra
    1.08
    Act Density 0.026%

    No Known Activations