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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating approval or greenlighting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "go" and "do."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dreams
    -0.62
    ĺħ
    -0.62
     symmetry
    -0.60
    $$$$
    -0.60
    undle
    -0.57
    ãģ®é
    -0.57
    RIC
    -0.56
     Provision
    -0.56
    Techn
    -0.55
     Topic
    -0.55
    POSITIVE LOGITS
    ables
    1.07
    ative
    0.88
    orm
    0.88
    ipers
    0.87
    orship
    0.87
    ibles
    0.87
    ings
    0.87
    able
    0.86
    ativity
    0.86
    outs
    0.84
    Act Density 0.137%

    No Known Activations