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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that discuss differences or relationships between groups

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    খন
    -0.52
    Safe
    -0.46
     manuales
    -0.46
    läufe
    -0.46
    ёз
    -0.46
    safe
    -0.45
     Safe
    -0.45
    blon
    -0.44
    zogen
    -0.43
    TaskList
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.70
    sizeCache
    0.69
     themſelves
    0.68
    ✨:
    0.67
    AddTagHelper
    0.66
     ProtoMessage
    0.66
    BagLayout
    0.66
     MNRAS
    0.66
    Erreferentziak
    0.65
    TagMode
    0.65
    Act Density 0.127%

    No Known Activations