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

    Neuronpedia

    INDEX
    Explanations

    equations or expressions that equal a value signified by the equals sign

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    basicConfig
    -0.58
     surla
    -0.56
    bea
    -0.51
     UIKit
    -0.49
    LayoutStyle
    -0.48
    TemporalType
    -0.48
     idea
    -0.48
    lytic
    -0.48
    Lithuania
    -0.47
     گوید
    -0.47
    POSITIVE LOGITS
    fjspx
    0.82
    abestanden
    0.72
    ſelves
    0.70
    migrationBuilder
    0.63
     pinulongan
    0.62
     GenerationType
    0.62
    wapV
    0.59
     itſelf
    0.58
     cauſe
    0.56
     poffe
    0.56
    Act Density 0.009%

    No Known Activations