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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their magnitudes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ))))
    -0.54
    )))),
    -0.53
    {}{
    -0.51
    __))
    -0.50
    ))
    -0.50
     <=",
    -0.49
    ><!--
    -0.49
    Global
    -0.49
    tagna
    -0.48
    фан
    -0.47
    POSITIVE LOGITS
     الحره
    0.73
    ſelf
    0.72
     Normdatei
    0.72
     houſe
    0.70
     avoient
    0.67
    StackNavigator
    0.67
     ExecuteAsync
    0.67
    reactstrap
    0.66
    substack
    0.65
     ſeveral
    0.65
    Act Density 0.024%

    No Known Activations