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

    Neuronpedia

    INDEX
    Explanations

    visual representations and relationships in data, particularly concerning sizes and correlations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     createSlice
    -0.64
    ThroughAttribute
    -0.61
    AndEndTag
    -0.58
    {§
    -0.56
    rzost
    -0.56
     giustizia
    -0.56
    udadera
    -0.55
    RoutingModule
    -0.55
     bpy
    -0.55
     oprot
    -0.55
    POSITIVE LOGITS
     representing
    0.74
     represent
    0.72
     represents
    0.69
     signify
    0.60
     signifies
    0.56
     Represents
    0.55
    representing
    0.54
     indicates
    0.54
     meant
    0.54
     signifie
    0.53
    Act Density 0.569%

    No Known Activations