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

    Neuronpedia

    INDEX
    Explanations

    phrases related to desirability and preferences in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.68
    AndEndTag
    -0.68
     vettor
    -0.65
     vectorielle
    -0.63
     puesta
    -0.62
     giudi
    -0.62
     tailings
    -0.61
     fatica
    -0.60
    utusan
    -0.59
     vettoriale
    -0.59
    POSITIVE LOGITS
    JsonFormat
    0.57
     wished
    0.57
     wish
    0.56
     desirable
    0.55
     ideal
    0.53
     want
    0.52
    irable
    0.52
    Ideally
    0.52
     indes
    0.51
    globalData
    0.50
    Act Density 0.024%

    No Known Activations