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

    Neuronpedia

    INDEX
    Explanations

    statements of conclusion or assertions made by a character in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndProject
    -0.58
    +:+
    -0.54
     conventional
    -0.52
     kami
    -0.47
     rouges
    -0.47
    gefahr
    -0.47
    </thead>
    -0.47
    getSupport
    -0.47
    Surely
    -0.47
    simum
    -0.46
    POSITIVE LOGITS
    LEncoder
    0.64
     MainAxisSize
    0.61
     SwiftUI
    0.60
    InitVars
    0.58
     geçir
    0.58
     dunes
    0.57
     invariance
    0.56
    dyž
    0.56
    eseorang
    0.55
     Asphalt
    0.55
    Act Density 0.013%

    No Known Activations