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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tasks, activities, or projects

    oai_token-act-pair · gpt-3.5-turbo

    themes related to human activities and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ().
    -0.71
    _.
    -0.67
     [&
    -0.63
    âĶĢâĶĢâĶĢâĶĢ
    -0.62
    *.
    -0.60
    ."[
    -0.59
    ).
    -0.58
    ).[
    -0.58
    .).
    -0.58
    ··
    -0.57
    POSITIVE LOGITS
    bilt
    0.58
     royalty
    0.57
    quartered
    0.57
    endon
    0.54
    adobe
    0.54
     Lunar
    0.54
    irtual
    0.51
     Expand
    0.50
    oppers
    0.50
    urrency
    0.49
    Act Density 1.912%

    No Known Activations