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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to building, creating, organizing, and arranging

    oai_token-act-pair · gpt-3.5-turbo

    actions related to creation or construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.88
     hampered
    -0.65
     guiActiveUnfocused
    -0.65
     [+]
    -0.64
    ocating
    -0.62
    MAT
    -0.61
    eks
    -0.59
    yond
    -0.59
     berth
    -0.59
    iners
    -0.59
    POSITIVE LOGITS
     himself
    0.80
     herself
    0.80
     copies
    0.69
    otom
    0.65
    ufact
    0.64
    ãĥį
    0.62
    ascript
    0.61
     her
    0.61
    ographs
    0.60
     his
    0.60
    Act Density 0.463%

    No Known Activations