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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing a definitive conclusion or statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritic
    -0.64
    knife
    -0.64
    FH
    -0.62
    rients
    -0.61
    reat
    -0.61
     downgrade
    -0.60
    yip
    -0.60
    aminer
    -0.58
    lift
    -0.58
    bal
    -0.57
    POSITIVE LOGITS
    ocating
    1.19
    uring
    1.09
    uding
    1.01
    usion
    0.96
    ocated
    0.94
     sorts
    0.88
    owing
    0.86
    ocation
    0.81
    usions
    0.80
    ergic
    0.78
    Act Density 0.056%

    No Known Activations