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

    Neuronpedia

    INDEX
    Explanations

    terms related to inherent or intrinsic qualities or properties

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    toMatchSnapshot
    -0.81
     يتيمه
    -0.79
    ActionTypes
    -0.70
     Vijay
    -0.68
    rizona
    -0.68
     CIE
    -0.65
    DockStyle
    -0.65
    ourable
    -0.64
    DateField
    -0.64
    ActionType
    -0.64
    POSITIVE LOGITS
     intrinsic
    1.01
     intrins
    1.01
    intrinsic
    0.95
     Intrinsic
    0.93
     intrinsically
    0.90
    inher
    0.86
    insic
    0.85
    Intrinsic
    0.84
     inherent
    0.83
     Chwiliwch
    0.79
    Act Density 0.009%

    No Known Activations