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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consent and data privacy

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.67
    LookAnd
    -0.65
     esboço
    -0.63
     MenuView
    -0.62
     mergeFrom
    -0.59
     resourceCulture
    -0.59
     GetEnumerator
    -0.59
     isomorphic
    -0.59
    ---*/
    -0.57
    SequentialGroup
    -0.56
    POSITIVE LOGITS
     preferences
    0.62
     الحره
    0.56
    Einstellungen
    0.49
    يميديا
    0.48
     pi
    0.47
    ⋙
    0.47
     prefers
    0.47
    EDEFAULT
    0.47
     preference
    0.47
     prof
    0.47
    Act Density 0.126%

    No Known Activations