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

    Neuronpedia

    INDEX
    Explanations

    data-related or technical terms associated with object properties and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Дереккөздер
    -0.77
    droje
    -0.75
     Beren
    -0.71
     occaf
    -0.69
     Baile
    -0.68
     Diſ
    -0.66
     recu
    -0.66
     Barclay
    -0.65
     themſelves
    -0.64
     itſelf
    -0.63
    POSITIVE LOGITS
    dt
    2.90
     dt
    2.51
    DT
    2.04
     DT
    1.91
    Dt
    1.65
     Dt
    1.59
    dts
    1.33
    dT
    0.93
    odt
    0.90
    ldt
    0.89
    Act Density 0.078%

    No Known Activations